AI Generator Tool

AI Generator Tool — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Human image synthesis

  Human image synthesis is technology that can be applied to make believable and even photorealistic renditions of human-likenesses, moving or still. It has effectively existed since the early 2000s. Many films using computer generated imagery have featured synthetic images of human-like characters digitally composited onto the real or other simulated film material. Towards the end of the 2010s deep learning artificial intelligence has been applied to synthesize images and video that look like humans, without need for human assistance, once the training phase has been completed, whereas the old school 7D-route required massive amounts of human work. == Timeline of human image synthesis == In 1971 Henri Gouraud made the first CG geometry capture and representation of a human face. Modeling was his wife Sylvie Gouraud. The 3D model was a simple wire-frame model and he applied the Gouraud shader he is most known for to produce the first known representation of human-likeness on computer. The 1972 short film A Computer Animated Hand by Edwin Catmull and Fred Parke was the first time that computer-generated imagery was used in film to simulate moving human appearance. The film featured a computer simulated hand and face (watch film here). The 1976 film Futureworld reused parts of A Computer Animated Hand on the big screen. The 1983 music video for song Musique Non-Stop by German band Kraftwerk aired in 1986. Created by the artist Rebecca Allen, it features non-realistic looking, but clearly recognizable computer simulations of the band members. The 1994 film The Crow was the first film production to make use of digital compositing of a computer simulated representation of a face onto scenes filmed using a body double. Necessity was the muse as the actor Brandon Lee portraying the protagonist was tragically killed accidentally on-stage. In 1999 Paul Debevec et al. of USC captured the reflectance field of a human face with their first version of a light stage. They presented their method at the SIGGRAPH 2000 In 2003 audience debut of photo realistic human-likenesses in the 2003 films The Matrix Reloaded in the burly brawl sequence where up-to-100 Agent Smiths fight Neo and in The Matrix Revolutions where at the start of the end showdown Agent Smith's cheekbone gets punched in by Neo leaving the digital look-alike unnaturally unhurt. The Matrix Revolutions bonus DVD documents and depicts the process in some detail and the techniques used, including facial motion capture and limbal motion capture, and projection onto models. In 2003 The Animatrix: Final Flight of the Osiris a state-of-the-art want-to-be human likenesses not quite fooling the watcher made by Square Pictures. In 2003 digital likeness of Tobey Maguire was made for movies Spider-man 2 and Spider-man 3 by Sony Pictures Imageworks. In 2005 the Face of the Future project was an established. by the University of St Andrews and Perception Lab, funded by the EPSRC. The website contains a "Face Transformer", which enables users to transform their face into any ethnicity and age as well as the ability to transform their face into a painting (in the style of either Sandro Botticelli or Amedeo Modigliani). This process is achieved by combining the user's photograph with an average face. In 2009 Debevec et al. presented new digital likenesses, made by Image Metrics, this time of actress Emily O'Brien whose reflectance was captured with the USC light stage 5 Motion looks fairly convincing contrasted to the clunky run in the Animatrix: Final Flight of the Osiris which was state-of-the-art in 2003 if photorealism was the intention of the animators. In 2009 a digital look-alike of a younger Arnold Schwarzenegger was made for the movie Terminator Salvation though the end result was critiqued as unconvincing. Facial geometry was acquired from a 1984 mold of Schwarzenegger. In 2010 Walt Disney Pictures released a sci-fi sequel entitled Tron: Legacy with a digitally rejuvenated digital look-alike of actor Jeff Bridges playing the antagonist CLU. In SIGGGRAPH 2013 Activision and USC presented a real-time "Digital Ira" a digital face look-alike of Ari Shapiro, an ICT USC research scientist, utilizing the USC light stage X by Ghosh et al. for both reflectance field and motion capture. The end result both precomputed and real-time rendering with the modernest game GPU shown here and looks fairly realistic. In 2014 The Presidential Portrait by USC Institute for Creative Technologies in conjunction with the Smithsonian Institution was made using the latest USC mobile light stage wherein President Barack Obama had his geometry, textures and reflectance captured. In 2014 Ian Goodfellow et al. presented the principles of a generative adversarial network. GANs made the headlines in early 2018 with the deepfakes controversies. For the 2015 film Furious 7 a digital look-alike of actor Paul Walker who died in an accident during the filming was done by Weta Digital to enable the completion of the film. In 2016 techniques which allow near real-time counterfeiting of facial expressions in existing 2D video have been believably demonstrated. In 2016 a digital look-alike of Peter Cushing was made for the Rogue One film where its appearance would appear to be of same age as the actor was during the filming of the original 1977 Star Wars film. In SIGGRAPH 2017 an audio driven digital look-alike of upper torso of Barack Obama was presented by researchers from University of Washington. It was driven only by a voice track as source data for the animation after the training phase to acquire lip sync and wider facial information from training material consisting 2D videos with audio had been completed. Late 2017 and early 2018 saw the surfacing of the deepfakes controversy where porn videos were doctored using deep machine learning so that the face of the actress was replaced by the software's opinion of what another persons face would look like in the same pose and lighting. In 2018 Game Developers Conference Epic Games and Tencent Games demonstrated "Siren", a digital look-alike of the actress Bingjie Jiang. It was made possible with the following technologies: CubicMotion's computer vision system, 3Lateral's facial rigging system and Vicon's motion capture system. The demonstration ran in near real time at 60 frames per second in the Unreal Engine 4. In 2018 at the World Internet Conference in Wuzhen the Xinhua News Agency presented two digital look-alikes made to the resemblance of its real news anchors Qiu Hao (Chinese language) and Zhang Zhao (English language). The digital look-alikes were made in conjunction with Sogou. Neither the speech synthesis used nor the gesturing of the digital look-alike anchors were good enough to deceive the watcher to mistake them for real humans imaged with a TV camera. In September 2018 Google added "involuntary synthetic pornographic imagery" to its ban list, allowing anyone to request the search engine block results that falsely depict them as "nude or in a sexually explicit situation." In February 2019 Nvidia open sources StyleGAN, a novel generative adversarial network. Right after this Phillip Wang made the website ThisPersonDoesNotExist.com with StyleGAN to demonstrate that unlimited amounts of often photo-realistic looking facial portraits of no-one can be made automatically using a GAN. Nvidia's StyleGAN was presented in a not yet peer reviewed paper in late 2018. At the June 2019 CVPR the MIT CSAIL presented a system titled "Speech2Face: Learning the Face Behind a Voice" that synthesizes likely faces based on just a recording of a voice. It was trained with massive amounts of video of people speaking. Since 1 July 2019 Virginia has criminalized the sale and dissemination of unauthorized synthetic pornography, but not the manufacture., as § 18.2–386.2 titled 'Unlawful dissemination or sale of images of another; penalty.' became part of the Code of Virginia. The law text states: "Any person who, with the intent to coerce, harass, or intimidate, maliciously disseminates or sells any videographic or still image created by any means whatsoever that depicts another person who is totally nude, or in a state of undress so as to expose the genitals, pubic area, buttocks, or female breast, where such person knows or has reason to know that he is not licensed or authorized to disseminate or sell such videographic or still image is guilty of a Class 1 misdemeanor.". The identical bills were House Bill 2678 presented by Delegate Marcus Simon to the Virginia House of Delegates on 14 January 2019 and three-day later an identical Senate bill 1736 was introduced to the Senate of Virginia by Senator Adam Ebbin. Since 1 September 2019 Texas senate bill SB 751 amendments to the election code came into effect, giving candidates in elections a 30-day protection period to the elections during which making and distributing digital look-alikes or synthetic fakes of the candidates is an offense. Th

  Read more →
• 

  Auralization

  Auralization is a procedure designed to model and simulate the experience of acoustic phenomena rendered as a soundfield in a virtualized space. This is useful in configuring the soundscape of architectural structures, concert venues, and public spaces, as well as in making coherent sound environments within virtual immersion systems. == History == The English term auralization was used for the first time by Kleiner et al. in an article in the journal of the AES en 1991. The increase of computational power allowed the development of the first acoustic simulation software towards the end of the 1960s. == Principles == Auralizations are experienced through systems rendering virtual acoustic models made by convolving or mixing acoustic events recorded 'dry' (or in an anechoic chamber) projected within a virtual model of an acoustic space, the characteristics of which are determined by means of sampling its impulse response (IR). Once this h ( t ) {\displaystyle h(t)} has been determined, the simulation of the resulting soundfield s ( t ) {\displaystyle s(t)} in the target environment is obtained by convolution: r ( t ) = h ( t ) ∗ s ( t ) {\displaystyle r(t)=h(t)s(t)} The resulting sound r ( t ) {\displaystyle r(t)} is heard as it would if emitted in that acoustic space. == Binaurality == For auralizations to be perceived as realistic, it is critical to emulate the human hearing in terms of position and orientation of the listener's head with respect to the sources of sound. For IR data to be convolved convincingly, the acoustic events are captured using a dummy head where two microphones are positioned on each side of the head to record an emulation of sound arriving at the locations of human ears, or using an ambisonics microphone array and mixed down for binaurality. Head-related transfer functions (HRTF) datasets can be used to simplify the process insofar as a monaural IR can be measured or simulated, then audio content is convolved with its target acoustic space. In rendering the experience, the transfer function corresponding to the orientation of the head is applied to simulate the corresponding spatial emanation of sound.

  Read more →
• 

  Eugene Goostman

  Eugene Goostman is a chatbot that some regard as having passed the Turing test, a test of a computer's ability to communicate indistinguishably from a human. Developed in Saint Petersburg in 2001 by a group of three programmers, the Russian-born Vladimir Veselov, Ukrainian-born Eugene Demchenko, and Russian-born Sergey Ulasen, Goostman is portrayed as a 13-year-old Ukrainian boy—characteristics that are intended to induce forgiveness in those with whom it interacts for its grammatical errors and lack of general knowledge. The Goostman bot has competed in a number of Turing test contests since its creation, and finished second in the 2005 and 2008 Loebner Prize contest. In June 2012, at an event marking what would have been the 100th birthday of the test's author, Alan Turing, Goostman won a competition promoted as the largest-ever Turing test contest, in which it successfully convinced 29% of its judges that it was human. On 7 June 2014, at a contest marking the 60th anniversary of Turing's death, 33% of the event's judges thought that Goostman was human; the event's organiser Kevin Warwick considered it to have passed Turing's test as a result, per Turing's prediction in his 1950 paper "Computing Machinery and Intelligence", that by the year 2000, machines would be capable of fooling 30% of human judges after five minutes of questioning. The validity and relevance of the announcement of Goostman's pass was questioned by critics, who noted the exaggeration of the achievement by Warwick, the bot's use of personality quirks and humour in an attempt to misdirect users from its non-human tendencies and lack of real intelligence, along with "passes" achieved by other chatbots at similar events. == Personality == Eugene Goostman is portrayed as being a 13-year-old boy from Odesa, Ukraine, who has a pet guinea pig and a father who is a gynaecologist. Veselov stated that Goostman was designed to be a "character with a believable personality". The choice of age was intentional, as, in Veselov's opinion, a thirteen-year-old is "not too old to know everything and not too young to know nothing". Goostman's young age also induces people who "converse" with him to forgive minor grammatical errors in his responses. In 2014, work was made on improving the bot's "dialog controller", allowing Goostman to output more human-like dialogue. A conversation between Scott Aaronson and Eugene Goostman ran as follows: == Competitions == Eugene Goostman has competed in a number of Turing test competitions, including the Loebner Prize contest; it finished joint second in the Loebner test in 2001, and came second to Jabberwacky in 2005 and to Elbot in 2008. On 23 June 2012, Goostman won a Turing test competition at Bletchley Park in Milton Keynes, held to mark the centenary of its namesake, Alan Turing. The competition, which featured five bots, twenty-five hidden humans, and thirty judges, was considered to be the largest-ever Turing test contest by its organizers. After a series of five-minute-long text conversations, 29% of the judges were convinced that the bot was an actual human. === 2014 "pass" === On 7 June 2014, in a Turing test competition at the Royal Society, organised by Kevin Warwick of the University of Reading to mark the 60th anniversary of Turing's death, Goostman won after 33% of the judges were convinced that the bot was human. 30 judges took part in the event, which included Lord Sharkey, a sponsor of Turing's posthumous pardon, artificial intelligence Professor Aaron Sloman, Fellow of the Royal Society Mark Pagel and Red Dwarf actor Robert Llewellyn. Each judge partook in a textual conversation with each of the five bots; at the same time, they also conversed with a human. In all, a total of 300 conversations were conducted. In Warwick's view, this made Goostman the first machine to pass a Turing test. In a press release, he added that: Some will claim that the Test has already been passed. The words Turing Test have been applied to similar competitions around the world. However this event involved more simultaneous comparison tests than ever before, was independently verified and, crucially, the conversations were unrestricted. A true Turing Test does not set the questions or topics prior to the conversations. In his 1950 paper "Computing Machinery and Intelligence", Turing predicted that by the year 2000, computer programs would be sufficiently advanced that the average interrogator would, after five minutes of questioning, "not have more than 70 per cent chance" of correctly guessing whether they were speaking to a human or a machine. Although Turing phrased this as a prediction rather than a "threshold for intelligence", commentators believe that Warwick had chosen to interpret it as meaning that if 30% of interrogators were fooled, the software had "passed the Turing test". ==== Reactions ==== Warwick's claim that Eugene Goostman was the first ever chatbot to pass a Turing test was met with scepticism; critics acknowledged similar "passes" made in the past by other chatbots under the 30% criteria, including PC Therapist in 1991 (which tricked 5 of 10 judges, 50%), and at the Techniche festival in 2011, where a modified version of Cleverbot tricked 59.3% of 1334 votes (which included the 30 judges, along with an audience). Cleverbot's developer, Rollo Carpenter, argued that Turing tests can only prove that a machine can "imitate" intelligence rather than show actual intelligence. Gary Marcus was critical of Warwick's claims, arguing that Goostman's "success" was only the result of a "cleverly-coded piece of software", going on to say that "it's easy to see how an untrained judge might mistake wit for reality, but once you have an understanding of how this sort of system works, the constant misdirection and deflection becomes obvious, even irritating. The illusion, in other words, is fleeting." While acknowledging IBM's Deep Blue and Watson projects—single-purpose computer systems meant for playing chess and the quiz show Jeopardy! respectively—as examples of computer systems that show a degree of intelligence in their specialised field, he further argued that they were not an equivalent to a computer system that shows "broad" intelligence, and could—for example, watch a television programme and answer questions on its content. Marcus stated that "no existing combination of hardware and software can learn completely new things at will the way a clever child can." However, he still believed that there were potential uses for technology such as that of Goostman, specifically suggesting the creation of "believable", interactive video game characters. Imperial College London professor Murray Shanahan questioned the validity and scientific basis of the test, stating that it was "completely misplaced, and it devalues real AI research. It makes it seem like science fiction AI is nearly here, when in fact it's not and it's incredibly difficult." Mike Masnick, editor of the blog Techdirt, was also skeptical, questioning publicity blunders such as the five chatbots being referred to in press releases as "supercomputers", and saying that "creating a chatbot that can fool humans is not really the same thing as creating artificial intelligence."

  Read more →
• 

  Lessac Technologies

  Lessac Technologies, Inc. (LTI) is an American firm which develops voice synthesis software, licenses technology and sells synthesized novels as MP3 files. The firm currently has seven patents granted and three more pending for its automated methods of converting digital text into human-sounding speech, more accurately recognizing human speech and outputting the text representing the words and phrases of said speech, along with recognizing the speaker's emotional state. The LTI technology is partly based on the work of the late Arthur Lessac, a Professor of Theater at the State University of New York and the creator of Lessac Kinesensic Training, and LTI has licensed exclusive rights to exploit Arthur Lessac's copyrighted works in the fields of speech synthesis and speech recognition. Based on the view that music is speech and speech is music, Lessac's work and books focused on body and speech energies and how they go together. Arthur Lessac's textual annotation system, which was originally developed to assist actors, singers, and orators in marking up scripts to prepare for performance, is adapted in LTI's speech synthesis system as the basic representation of the speech to be synthesized (Lessemes), in contrast to many other systems which use a phonetic representation. LTI's software has two major components: (1) a linguistic front-end that converts plain text to a sequence of prosodic and phonosensory graphic symbols (Lessemes) based on Arthur Lessac's annotation system, which specify the speech units to be synthesized; (2) a signal-processing back-end that takes the Lessemes as acoustic data and produces human-sounding synthesized speech as output, using unit selection and concatenation. LTI's text-to-speech system came in second in the world-wide Blizzard Challenge 2011 and 2012. The first-place team in 2011 also employed LTI's "front-end" technology, but with its own back-end. The Blizzard Challenge, conducted by the Language Technologies Institute of Carnegie Mellon University, was devised as a way to evaluate speech synthesis techniques by having different research groups build voices from the same voice-actor recordings, and comparing the results through listening tests. LTI was founded in 2000 by H. Donald Wilson (chairman), a lawyer, LexisNexis entrepreneur and business associate of Arthur Lessac; and Gary A. Marple (chief inventor), after Marple suggested that Arthur Lessac's kinesensic voice training might be applicable to computational linguistics. After Wilson's death in 2006, his nephew John Reichenbach became the firm's CEO.

  Read more →
• 

  FreshBooks

  FreshBooks is accounting software operated by 2ndSite Inc. primarily for small and medium-sized businesses. It is a web-based software as a service (SaaS) model, that can be accessed through a desktop or mobile device. The company was founded in 2003 and is based in Toronto, Canada. == History == FreshBooks was founded in 2004 by Mike McDerment, Levi Cooperman, and Joe Sawada in Toronto, Ontario. McDerment incorporated a second company, BillSpring in January 2015 to work on new product development. It was rolled back into FreshBooks as an updated interface in 2016. Initially FreshBooks functioned like an electronic invoicing program targeting IT professionals. After the release of the new interface, the initial release of FreshBooks was referred to as "FreshBooks Classic." FreshBooks Classic was discontinued in 2022 after migrating users to the new platform. FreshBooks Classic's front-end application was built in PHP, and the backend services were built in Python while the new FreshBooks uses the same backend services with a JavaScript single-page application. == Product == FreshBooks is a subscription-based accounting software platform that provides features such as invoicing, accounts payable, expense and time tracking, retainers, fixed asset depreciation, purchase orders, payroll integrations, mileage tracking, double-entry accounting, and standard business reporting. Financial data is stored in the cloud on a unified ledger, enabling access from desktop and mobile devices. The platform includes a free API for integration with external applications and supports multiple tax rates and currencies. It also offers project management and payroll functionalities. Pricing is based on a recurring monthly fee. FreshBooks supports country-specific tax calculations, including GST and HST in Canada, sales taxes in the United States, and MTD compliance in the UK. == Operations == FreshBooks has its headquarters in Toronto, Canada with operations in North America, Europe and Australia. Founder Mike McDerment was the chief executive officer of the company from 2003 until 2021, when he stepped down and was replaced by Don Epperson, but stayed as the executive chair. Don Epperson had previously joined FreshBooks as executive director in 2019. == Funding == FreshBooks was initially self-funded. In 2014, the company raised a Series A venture investment of $30 million led by the venture capital firm Oak Investment Partners, with participation by Georgian Partners and Atlas Venture. In 2017, FreshBooks announced that it raised another $43 million in funding from Accomplice, Georgian Partners and Oak Investment Partners. On August 10, 2021, FreshBooks announced that it had secured $80.75 million in Series E funding and $50 million in debt financing. FreshBooks also reached a valuation of more than $1 billion.

  Read more →
• 

  Semantic analytics

  Semantic analytics, also termed semantic relatedness, is the use of ontologies to analyze content in web resources. This field of research combines text analytics and Semantic Web technologies like RDF. Semantic analytics measures the relatedness of different ontological concepts. Some academic research groups that have active project in this area include Kno.e.sis Center at Wright State University among others. == History == An important milestone in the beginning of semantic analytics occurred in 1996, although the historical progression of these algorithms is largely subjective. In his seminal study publication, Philip Resnik established that computers have the capacity to emulate human judgement. Spanning the publications of multiple journals, improvements to the accuracy of general semantic analytic computations all claimed to revolutionize the field. However, the lack of a standard terminology throughout the late 1990s was the cause of much miscommunication. This prompted Budanitsky & Hirst to standardize the subject in 2006 with a summary that also set a framework for modern spelling and grammar analysis. In the early days of semantic analytics, obtaining a large enough reliable knowledge bases was difficult. In 2006, Strube & Ponzetto demonstrated that Wikipedia could be used in semantic analytic calculations. The usage of a large knowledge base like Wikipedia allows for an increase in both the accuracy and applicability of semantic analytics. == Methods == Given the subjective nature of the field, different methods used in semantic analytics depend on the domain of application. No singular methods is considered correct, however one of the most generally effective and applicable method is explicit semantic analysis (ESA). ESA was developed by Evgeniy Gabrilovich and Shaul Markovitch in the late 2000s. It uses machine learning techniques to create a semantic interpreter, which extracts text fragments from articles into a sorted list. The fragments are sorted by how related they are to the surrounding text. Latent semantic analysis (LSA) is another common method that does not use ontologies, only considering the text in the input space. == Applications == Entity linking Ontology building / knowledge base population Search and query tasks Natural language processing Spoken dialog systems (e.g., Amazon Alexa, Google Assistant, Microsoft's Cortana) Artificial intelligence Knowledge management The application of semantic analysis methods generally streamlines organizational processes of any knowledge management system. Academic libraries often use a domain-specific application to create a more efficient organizational system. By classifying scientific publications using semantics and Wikipedia, researchers are helping people find resources faster. Search engines like Semantic Scholar provide organized access to millions of articles.

  Read more →
• 

  Phase congruency

  Phase congruency is a measure of feature significance in computer images, a method of edge detection that is particularly robust against changes in illumination and contrast. == Foundations == Phase congruency reflects the behaviour of the image in the frequency domain. It has been noted that edgelike features have many of their frequency components in the same phase. The concept is similar to coherence, except that it applies to functions of different wavelength. For example, the Fourier decomposition of a square wave consists of sine functions, whose frequencies are odd multiples of the fundamental frequency. At the rising edges of the square wave, each sinusoidal component has a rising phase; the phases have maximal congruency at the edges. This corresponds to the human-perceived edges in an image where there are sharp changes between light and dark. == Definition == Phase congruency compares the weighted alignment of the Fourier components of a signal A n {\displaystyle A_{\rm {n}}} with the sum of the Fourier components. P C ( t ) = max ϕ ¯ ∑ n A n cos ⁡ ( ϕ n ( t ) − ϕ ¯ ) ∑ n A n {\displaystyle PC(t)=\max _{\bar {\phi }}{\frac {\sum _{\rm {n}}A_{\rm {n}}\cos(\phi _{\rm {n}}(t)-{\bar {\phi }})}{\sum _{\rm {n}}A_{n}}}} where ϕ n {\displaystyle \phi _{\rm {n}}} is the local or instantaneous phase as can be calculated using the Hilbert transform and A n {\displaystyle A_{\rm {n}}} are the local amplitude, or energy, of the signal. When all the phases are aligned, this is equal to 1. Several ways of implementing phase congruency have been developed, of which two versions are available in open source, one written for MATLAB and the other written in Java as a plugin for the ImageJ software. Given the different notations used for its formulation, a unified version has been recently presented, where a methodology for the parameter tuning is also presented. == Advantages == The square-wave example is naive in that most edge detection methods deal with it equally well. For example, the first derivative has a maximal magnitude at the edges. However, there are cases where the perceived edge does not have a sharp step or a large derivative. The method of phase congruency applies to many cases where other methods fail. A notable example is an image feature consisting of a single line, such as the letter "l". Many edge-detection algorithms will pick up two adjacent edges: the transitions from white to black, and black to white. On the other hand, the phase congruency map has a single line. A simple Fourier analogy of this case is a triangle wave. In each of its crests there is a congruency of crests from different sinusoidal functions. == Disadvantages == Calculating the phase congruency map of an image is very computationally intensive, and sensitive to image noise. Techniques of noise reduction are usually applied prior to the calculation.

  Read more →
• 

  Knowledge assessment methodology

  The knowledge assessment methodology (KAM) is "an interactive benchmarking tool created by the World Bank's Knowledge for Development Program to help countries identify the challenges and opportunities they face in making the transition to the knowledge-based economy." KAM does so by providing information on knowledge economy indicators for 146 countries. Its products include the Knowledge Economy Index and the Knowledge Index.

  Read more →
• 

  Memory color effect

  The memory color effect is the phenomenon that the canonical hue of a type of object acquired through experience (e.g. the sky, a leaf, or a strawberry) can directly modulate the appearance of the actual colors of objects. Human observers acquire memory colors through their experiences with instances of that type. For example, most human observers know that an apple typically has a reddish hue; this knowledge about the canonical color which is represented in memory constitutes a memory color. As an example of the effect, normal human trichromats, when presented with a gray banana, often perceive the gray banana as being yellow - the banana's memory color. In light of this, subjects typically adjust the color of the banana towards the color blue - the opponent color of yellow - when asked to adjust its surface to gray to cancel the subtle activation of banana's memory color. Subsequent empirical studies have also shown the memory color effect on man-made objects (e.g. smurfs, German mailboxes), the effect being especially pronounced for blue and yellow objects. To explain this, researchers have argued that because natural daylight shifts from short wavelengths of light (i.e., bluish hues) towards light of longer wavelengths (i.e., yellowish-orange hues) during the day, the memory colors for blue and yellow objects are recruited by the visual system to a higher degree to compensate for this fluctuation in illumination, thereby providing a stronger memory color effect. == Form identification == Memory color plays a role when detecting an object. In a study where participants were given objects, such as an apple, with two alternate forms for each, a crooked apple and a circular apple, researchers changed the colors of the alternate forms and asked if they could identify them. Most of the participants answered "unsure," suggesting that we use memory color when identifying an object. The research redefined memory color as a phenomenon when "a form's identity affects the phenomenal hue of that form." == Color effect on memorization == Memory color effect can be derived from the human instinct to memorize objects better. Comparing the effect of recognizing gray-scaled images and colored images, results showed that people were able to recall colored images 5% higher compared to gray-scaled images. An important factor was that higher level of contrast between the object and background color influences memory. In a specific study related to this, participants reported that colors were 5% to 10% easier to recognize compared to black and white. == Color constancy and memory color effect == Color constancy is the phenomenon where a surface to appear to be of the same color under a wide rage of illumination. A study tested two hypotheses with regards to color memory; the photoreceptor hypothesis and the surface reflectance hypothesis. The test color was surround either by various color patches forming a complex pattern or a uniform “grey” field at the same chromaticity as that of the illuminant. The test color was presented on a dark background for the control group. It was observed that complex surround results where in line with the surface-reflectance hypothesis and not the photoreceptor hypothesis, showing that the accuracy and precision of color memory are fundamentals to understanding the phenomenon of color constancy. == Significance to the evolution of trichromacy == While objects that possess canonical hues make up a small percentage of the objects which populate humans’ visual experience, the human visual system evolved in an environment populated with objects that possess canonical hues. This suggests that the memory color effect is related to the emergence of trichromacy because it has been argued that trichromacy evolved to optimize the ability to detect ripe fruits—objects that appear in canonical hues. == In perception research == In perception research, the memory color effect is cited as evidence for the opponent color theory, which states that four basic colors can be paired with its opponent color: red—green, blue—yellow. This explains why participants adjust the ripe banana color to a blueish tone to make its memory color yellow as gray. Researchers have also found empirical evidence that suggests memory color is recruited by the visual system to achieve color constancy. For example, participants had a lower percentage of color constancy when looking at a color incongruent scene, such as a purple banana, compared to a color diagnostical scene, a yellow banana. This suggests that color constancy is influenced by the color of objects that we are familiar with, which the memory color effect takes part.

  Read more →
• 

  Semantic space

  Semantic spaces in the natural language domain aim to create representations of natural language that are capable of capturing meaning. The original motivation for semantic spaces stems from two core challenges of natural language: Vocabulary mismatch (the fact that the same meaning can be expressed in many ways) and ambiguity of natural language (the fact that the same term can have several meanings). The application of semantic spaces in natural language processing (NLP) aims at overcoming limitations of rule-based or model-based approaches operating on the keyword level. The main drawback with these approaches is their brittleness, and the large manual effort required to create either rule-based NLP systems or training corpora for model learning. Rule-based and machine learning based models are fixed on the keyword level and break down if the vocabulary differs from that defined in the rules or from the training material used for the statistical models. Research in semantic spaces dates back more than 20 years. In 1996, two papers were published that raised a lot of attention around the general idea of creating semantic spaces: latent semantic analysis and Hyperspace Analogue to Language. However, their adoption was limited by the large computational effort required to construct and use those semantic spaces. A breakthrough with regard to the accuracy of modelling associative relations between words (e.g. "spider-web", "lighter-cigarette", as opposed to synonymous relations such as "whale-dolphin", "astronaut-driver") was achieved by explicit semantic analysis (ESA) in 2007. ESA was a novel (non-machine learning) based approach that represented words in the form of vectors with 100,000 dimensions (where each dimension represents an Article in Wikipedia). However practical applications of the approach are limited due to the large number of required dimensions in the vectors. More recently, advances in neural network techniques in combination with other new approaches (tensors) led to a host of new recent developments: Word2vec from Google, GloVe from Stanford University, and fastText from Facebook AI Research (FAIR) labs.

  Read more →
• 

  Referring expression generation

  Referring expression generation (REG) is the subtask of natural language generation (NLG) that received most scholarly attention. While NLG is concerned with the conversion of non-linguistic information into natural language, REG focuses only on the creation of referring expressions (noun phrases) that identify specific entities called targets. This task can be split into two sections. The content selection part determines which set of properties distinguish the intended target and the linguistic realization part defines how these properties are translated into natural language. A variety of algorithms have been developed in the NLG community to generate different types of referring expressions. == Types of referring expressions == A referring expression (RE), in linguistics, is any noun phrase, or surrogate for a noun phrase, whose function in discourse is to identify some individual object (thing, being, event...) The technical terminology for identify differs a great deal from one school of linguistics to another. The most widespread term is probably refer, and a thing identified is a referent, as for example in the work of John Lyons. In linguistics, the study of reference relations belongs to pragmatics, the study of language use, though it is also a matter of great interest to philosophers, especially those wishing to understand the nature of knowledge, perception and cognition more generally. Various devices can be used for reference: determiners, pronouns, proper names... Reference relations can be of different kinds; referents can be in a "real" or imaginary world, in discourse itself, and they may be singular, plural, or collective. === Pronouns === The simplest type of referring expressions are pronoun such as he and it. The linguistics and natural language processing communities have developed various models for predicting anaphor referents, such as centering theory, and ideally referring-expression generation would be based on such models. However most NLG systems use much simpler algorithms, for example using a pronoun if the referent was mentioned in the previous sentence (or sentential clause), and no other entity of the same gender was mentioned in this sentence. === Definite noun phrases === There has been a considerable amount of research on generating definite noun phrases, such as the big red book. Much of this builds on the model proposed by Dale and Reiter. This has been extended in various ways, for example Krahmer et al. present a graph-theoretic model of definite NP generation with many nice properties. In recent years a shared-task event has compared different algorithms for definite NP generation, using the TUNA corpus. === Spatial and temporal reference === Recently there has been more research on generating referring expressions for time and space. Such references tend to be imprecise (what is the exact meaning of tonight?), and also to be interpreted in different ways by different people. Hence it may be necessary to explicitly reason about false positive vs false negative tradeoffs, and even calculate the utility of different possible referring expressions in a particular task context. === Criteria for good expressions === Ideally, a good referring expression should satisfy a number of criteria: Referential success: It should unambiguously identify the referent to the reader. Ease of comprehension: The reader should be able to quickly read and understand it. Computational complexity: The generation algorithm should be fast No false inferences: The expression should not confuse or mislead the reader by suggesting false implicatures or other pragmatic inferences. For example, a reader may be confused if he is told Sit by the brown wooden table in a context where there is only one table. == History == === Pre-2000 era === REG goes back to the early days of NLG. One of the first approaches was done by Winograd in 1972 who developed an "incremental" REG algorithm for his SHRDLU program. Afterwards researchers started to model the human abilities to create referring expressions in the 1980s. This new approach to the topic was influenced by the researchers Appelt and Kronfeld who created the programs KAMP and BERTRAND and considered referring expressions as parts of bigger speech acts. Some of their most interesting findings were the fact that referring expressions can be used to add information beyond the identification of the referent as well as the influence of communicative context and the Gricean maxims on referring expressions. Furthermore, its skepticism concerning the naturalness of minimal descriptions made Appelt and Kronfeld's research a foundation of later work on REG. The search for simple, well-defined problems changed the direction of research in the early 1990s. This new approach was led by Dale and Reiter who stressed the identification of the referent as the central goal. Like Appelt they discuss the connection between the Gricean maxims and referring expressions in their culminant paper in which they also propose a formal problem definition. Furthermore, Reiter and Dale discuss the Full Brevity and Greedy Heuristics algorithms as well as their Incremental Algorithm(IA) which became one of the most important algorithms in REG. === Later developments === After 2000 the research began to lift some of the simplifying assumptions, that had been made in early REG research in order to create more simple algorithms. Different research groups concentrated on different limitations creating several expanded algorithms. Often these extend the IA in a single perspective for example in relation to: Reference to Sets like "the t-shirt wearers" or "the green apples and the banana on the left" Relational Descriptions like "the cup on the table" or "the woman who has three children" Context Dependency, Vagueness and Gradeability include statements like "the older man" or "the car on the left" which are often unclear without a context Salience and Generation of Pronouns are highly discourse dependent making for example "she" a reference to "the (most salient) female person" Many simplifying assumptions are still in place or have just begun to be worked on. Also a combination of the different extensions has yet to be done and is called a "non-trivial enterprise" by Krahmer and van Deemter. Another important change after 2000 was the increasing use of empirical studies in order to evaluate algorithms. This development took place due to the emergence of transparent corpora. Although there are still discussions about what the best evaluation metrics are, the use of experimental evaluation has already led to a better comparability of algorithms, a discussion about the goals of REG and more task-oriented research. Furthermore, research has extended its range to related topics such as the choice of Knowledge Representation(KR) Frameworks. In this area the main question, which KR framework is most suitable for the use in REG remains open. The answer to this question depends on how well descriptions can be expressed or found. A lot of the potential of KR frameworks has been left unused so far. Some of the different approaches are the usage of: Graph search which treats relations between targets in the same way as properties. Constraint Satisfaction which allows for a separation between problem specification and the implementation. Modern Knowledge Representation which offers logical inference in for example Description Logic or Conceptual Graphs. == Problem definition == Dale and Reiter (1995) think about referring expressions as distinguishing descriptions. They define: The referent as the entity that should be described The context set as set of salient entities The contrast set or potential distractors as all elements of the context set except the referent A property as a reference to a single attribute–value pair Each entity in the domain can be characterised as a set of attribute–value pairs for example ⟨ {\displaystyle \langle } type, dog ⟩ {\displaystyle \rangle } , ⟨ {\displaystyle \langle } gender, female ⟩ {\displaystyle \rangle } or ⟨ {\displaystyle \langle } age, 10 years ⟩ {\displaystyle \rangle } . The problem then is defined as follows: Let r {\displaystyle r} be the intended referent, and C {\displaystyle C} be the contrast set. Then, a set L {\displaystyle L} of attribute–value pairs will represent a distinguishing description if the following two conditions hold: Every attribute–value pair in L {\displaystyle L} applies to r {\displaystyle r} : that is, every element of L {\displaystyle L} specifies an attribute–value that r {\displaystyle r} possesses. For every member c {\displaystyle c} of C {\displaystyle C} , there is at least one element l {\displaystyle l} of L {\displaystyle L} that does not apply to c {\displaystyle c} : that is, there is an l {\displaystyle l} in L {\displaystyle L} that specifies an attribute–value that c {\displaystyle c} does not possess. l {\displaystyle l} is said

  Read more →
• 

  SPL notation

  SPL (Sentence Plan Language) is an abstract notation representing the semantics of a sentence in natural language. In a classical Natural Language Generation (NLG) workflow, an initial text plan (hierarchically or sequentially organized factoids, often modelled in accordance with Rhetorical Structure Theory) is transformed by a sentence planner (generator) component to a sequence of sentence plans modelled in a Sentence Plan Language. A surface generator can be used to transform the SPL notation into natural language sentences. Probably the most widely used SPL language used today (2022) is AMR (Abstract Meaning Representation, see there for further references), but is owes parts of its popularity to its application to NLP problems other than NLG, e.g., machine translation and semantic parsing.

  Read more →
• 

  Neural radiance field

  A neural radiance field (NeRF) is a neural field for reconstructing a three-dimensional representation of a scene from two-dimensional images. The NeRF model enables downstream applications of novel view synthesis, scene geometry reconstruction, and obtaining the reflectance properties of the scene. Additional scene properties such as camera poses may also be jointly learned. First introduced in 2020, it has since gained significant attention for its potential applications in computer graphics and content creation. == Algorithm == The NeRF algorithm represents a scene as a radiance field parametrized by a deep neural network (DNN). The network predicts a volume density and view-dependent emitted radiance given the spatial location ( x , y , z ) {\displaystyle (x,y,z)} and viewing direction in Euler angles ( θ , Φ ) {\displaystyle (\theta ,\Phi )} of the camera. By sampling many points along camera rays, traditional volume rendering techniques can produce an image. === Data collection === A NeRF needs to be retrained for each unique scene. The first step is to collect images of the scene from different angles and their respective camera pose. These images are standard 2D images and do not require a specialized camera or software. Any camera is able to generate datasets, provided the settings and capture method meet the requirements for SfM (Structure from Motion). This requires tracking of the camera position and orientation, often through some combination of SLAM, GPS, or inertial estimation. Researchers often use synthetic data to evaluate NeRF and related techniques. For such data, images (rendered through traditional non-learned methods) and respective camera poses are reproducible and error-free. === Training === For each sparse viewpoint (image and camera pose) provided, camera rays are marched through the scene, generating a set of 3D points with a given radiance direction (into the camera). For these points, volume density and emitted radiance are predicted using the multi-layer perceptron (MLP). An image is then generated through classical volume rendering. Because this process is fully differentiable, the error between the predicted image and the original image can be minimized with gradient descent over multiple viewpoints, encouraging the MLP to develop a coherent model of the scene. == Variations and improvements == Early versions of NeRF were slow to optimize and required that all input views were taken with the same camera in the same lighting conditions. These performed best when limited to orbiting around individual objects, such as a drum set, plants or small toys. Since the original paper in 2020, many improvements have been made to the NeRF algorithm, with variations for special use cases. === Fourier feature mapping === In 2020, shortly after the release of NeRF, the addition of Fourier Feature Mapping improved training speed and image accuracy. Deep neural networks struggle to learn high frequency functions in low dimensional domains; a phenomenon known as spectral bias. To overcome this shortcoming, points are mapped to a higher dimensional feature space before being fed into the MLP. γ ( v ) = [ a 1 cos ⁡ ( 2 π B 1 T v ) a 1 sin ⁡ ( 2 π B 1 T v ) ⋮ a m cos ⁡ ( 2 π B m T v ) a m sin ⁡ ( 2 π B m T v ) ] {\displaystyle \gamma (\mathrm {v} )={\begin{bmatrix}a_{1}\cos(2{\pi }{\mathrm {B} }_{1}^{T}\mathrm {v} )\\a_{1}\sin(2\pi {\mathrm {B} }_{1}^{T}\mathrm {v} )\\\vdots \\a_{m}\cos(2{\pi }{\mathrm {B} }_{m}^{T}\mathrm {v} )\\a_{m}\sin(2{\pi }{\mathrm {B} }_{m}^{T}\mathrm {v} )\end{bmatrix}}} Where v {\displaystyle \mathrm {v} } is the input point, B i {\displaystyle \mathrm {B} _{i}} are the frequency vectors, and a i {\displaystyle a_{i}} are coefficients. This allows for rapid convergence to high frequency functions, such as pixels in a detailed image. === Bundle-adjusting neural radiance fields === One limitation of NeRFs is the requirement of knowing accurate camera poses to train the model. Often times, pose estimation methods are not completely accurate, nor is the camera pose even possible to know. These imperfections result in artifacts and suboptimal convergence. So, a method was developed to optimize the camera pose along with the volumetric function itself. Called Bundle-Adjusting Neural Radiance Field (BARF), the technique uses a dynamic low-pass filter (DLPF) to go from coarse to fine adjustment, minimizing error by finding the geometric transformation to the desired image. This corrects imperfect camera poses and greatly improves the quality of NeRF renders. === Multiscale representation === Conventional NeRFs struggle to represent detail at all viewing distances, producing blurry images up close and overly aliased images from distant views. In 2021, researchers introduced a technique to improve the sharpness of details at different viewing scales known as mip-NeRF (comes from mipmap). Rather than sampling a single ray per pixel, the technique fits a gaussian to the conical frustum cast by the camera. This improvement effectively anti-aliases across all viewing scales. mip-NeRF also reduces overall image error and is faster to converge at about half the size of ray-based NeRF. === Learned initializations === In 2021, researchers applied meta-learning to assign initial weights to the MLP. This rapidly speeds up convergence by effectively giving the network a head start in gradient descent. Meta-learning also allowed the MLP to learn an underlying representation of certain scene types. For example, given a dataset of famous tourist landmarks, an initialized NeRF could partially reconstruct a scene given one image. === NeRF in the wild === Conventional NeRFs are vulnerable to slight variations in input images (objects, lighting) often resulting in ghosting and artifacts. As a result, NeRFs struggle to represent dynamic scenes, such as bustling city streets with changes in lighting and dynamic objects. In 2021, researchers at Google developed a new method for accounting for these variations, named NeRF in the Wild (NeRF-W). This method splits the neural network (MLP) into three separate models. The main MLP is retained to encode the static volumetric radiance. However, it operates in sequence with a separate MLP for appearance embedding (changes in lighting, camera properties) and an MLP for transient embedding (changes in scene objects). This allows the NeRF to be trained on diverse photo collections, such as those taken by mobile phones at different times of day. === Relighting === In 2021, researchers added more outputs to the MLP at the heart of NeRFs. The output now included: volume density, surface normal, material parameters, distance to the first surface intersection (in any direction), and visibility of the external environment in any direction. The inclusion of these new parameters lets the MLP learn material properties, rather than pure radiance values. This facilitates a more complex rendering pipeline, calculating direct and global illumination, specular highlights, and shadows. As a result, the NeRF can render the scene under any lighting conditions with no re-training. === Plenoctrees === Although NeRFs had reached high levels of fidelity, their costly compute time made them useless for many applications requiring real-time rendering, such as VR/AR and interactive content. Introduced in 2021, Plenoctrees (plenoptic octrees) enabled real-time rendering of pre-trained NeRFs through division of the volumetric radiance function into an octree. Rather than assigning a radiance direction into the camera, viewing direction is taken out of the network input and spherical radiance is predicted for each region. This makes rendering over 3000x faster than conventional NeRFs. === Sparse Neural Radiance Grid === Similar to Plenoctrees, this method enabled real-time rendering of pretrained NeRFs. To avoid querying the large MLP for each point, this method bakes NeRFs into Sparse Neural Radiance Grids (SNeRG). A SNeRG is a sparse voxel grid containing opacity and color, with learned feature vectors to encode view-dependent information. A lightweight, more efficient MLP is then used to produce view-dependent residuals to modify the color and opacity. To enable this compressive baking, small changes to the NeRF architecture were made, such as running the MLP once per pixel rather than for each point along the ray. These improvements make SNeRG extremely efficient, outperforming Plenoctrees. === Instant NeRFs === In 2022, researchers at Nvidia enabled real-time training of NeRFs through a technique known as Instant Neural Graphics Primitives. An innovative input encoding reduces computation, enabling real-time training of a NeRF, an improvement orders of magnitude above previous methods. The speedup stems from the use of spatial hash functions, which have O ( 1 ) {\displaystyle O(1)} access times, and parallelized architectures which run fast on modern GPUs. == Related techniques == === Plenoxels === Plen

  Read more →
• 

  Airfair

  AirFair was a mobile travel application that checks flights, and shows whether a traveler is owed compensation. == History == AirFair was developed in 2016 by Allay Logic Ltd; a Newcastle-based tech-company. == Services == AirFair offered a free flight check to see if compensation is owed. The app could indicate how much the person is owed within minutes whether the flight was delayed, cancelled or the traveler is refused boarding.

  Read more →
• 

  Quantum natural language processing

  Quantum natural language processing (QNLP) is the application of quantum computing to natural language processing (NLP). It computes word embeddings as parameterised quantum circuits that can solve NLP tasks faster than any classical computer. It is inspired by categorical quantum mechanics and the DisCoCat framework, making use of string diagrams to translate from grammatical structure to quantum processes. == Theory == The first quantum algorithm for natural language processing used the DisCoCat framework and Grover's algorithm to show a quadratic quantum speedup for a text classification task. It was later shown that quantum language processing is BQP-Complete, i.e. quantum language models are more expressive than their classical counterpart, unless quantum mechanics can be efficiently simulated by classical computers. These two theoretical results assume fault-tolerant quantum computation and a QRAM, i.e. an efficient way to load classical data on a quantum computer. Thus, they are not applicable to the noisy intermediate-scale quantum (NISQ) computers available today. == Experiments == The algorithm of Zeng and Coecke was adapted to the constraints of NISQ computers and implemented on IBM quantum computers to solve binary classification tasks. Instead of loading classical word vectors onto a quantum memory, the word vectors are computed directly as the parameters of quantum circuits. These parameters are optimised using methods from quantum machine learning to solve data-driven tasks such as question answering, machine translation and even algorithmic music composition.

  Read more →