Glossary: Difference between revisions

= Adequate Porn Watcher AI =

= Appearance and voice theft =

----

* 2 for the entry angle

* 2 for the exit angle of the light.

----

= Burqa =

[[File:20180613 Folkemodet Bornholm burka happening 0118 (42739707262).jpg|thumb|right|300px|Some humans in [[w:burqa]]s a the Bornholm burka happening]]

{{Q|A '''burqa''', also known as '''chadri''' or [[w:paranja|paranja]] in [[w:Central Asia|Central Asia]], is an enveloping outer garment worn by women in some Islamic traditions to cover themselves in public, which covers the body and the face.|Wikipedia|[[w:burqa|burqa]]s}}

----

= Covert modeling =

'''Covert modeling''' refers to both covertly modeling aspects of a subject i.e. without express consent.

* Covertly modeling the '''human voice'''

There is work ongoing to model e.g. '''human's style of writing''', but this is probably not as drastic a threat as the covert modeling of appearance and of voice.

----

{{Q|'''Deepfake''' (a [[w:portmanteau|portmanteau]] of "[[w:deep learning|deep learning]]" and "fake") is a technique for [[w:human image synthesis|human image synthesis]] based on [[w:artificial intelligence|artificial intelligence]]. It is used to combine and [[w:Superimposition|superimpose]] existing images and videos onto source images or videos using a machine learning technique called a "[[w:generative adversarial network|generative adversarial network]]" (GAN).|Wikipedia|[[w:Deepfake|Deepfake]]s}}

----

* [https://www.darpa.mil/program/media-forensics '''DARPA program: 'Media Forensics (MediFor)'''' at darpa.mil] since 2016

* [https://www.darpa.mil/program/semantic-forensics '''DARPA program: 'Semantic Forensics (SemaFor)''' at darpa.mil] since 2019

----

= Digital look-alike =

----

= Digital sound-alike =

----

{{Q|A '''generative adversarial network''' ('''GAN''') is a class of [[w:machine learnin|g]] systems. Two [[w:neural network|neural network]]s contest with each other in a [[w:zero-sum game|zero-sum game]] framework. This technique can generate photographs that look at least superficially authentic to human observers,<ref name="GANs">{{cite arXiv |eprint=1406.2661|title=Generative Adversarial Networks|first1=Ian |last1=Goodfellow |first2=Jean |last2=Pouget-Abadie |first3=Mehdi |last3=Mirza |first4=Bing |last4=Xu |first5=David |last5=Warde-Farley |first6=Sherjil |last6=Ozair |first7=Aaron |last7=Courville |first8=Yoshua |last8=Bengio |class=cs.LG |year=2014 }}</ref> having many realistic characteristics. It is a form of [[w:unsupervised learning|unsupervised learning]]]].<ref name="ITT_GANs">{{cite arXiv |eprint=1606.03498|title=Improved Techniques for Training GANs|last1=Salimans |first1=Tim |last2=Goodfellow |first2=Ian |last3=Zaremba |first3=Wojciech |last4=Cheung |first4=Vicki |last5=Radford |first5=Alec |last6=Chen |first6=Xi |class=cs.LG |year=2016 }}</ref>|Wikipedia|[[w:generative adversarial network|generative adversarial networks]]}}

----

= Human image synthesis =

{{Q|'''Human image synthesis''' can be applied to make believable and even [[w:photorealism|photorealistic]] of human-likenesses, moving or still. This has effectively been the situation since the early [[w:2000s (decade)|2000s]]. Many films using [[w:computer generated imagery|computer generated imagery]] have featured synthetic images of human-like characters [[w:digital compositing|digitally composited]] onto the real or other simulated film material.|Wikipedia|[[w:Human image synthesis|Human image syntheses]]}}

----

= Institute for Creative Technologies =

The '''[[w:Institute for Creative Technologies|Institute for Creative Technologies]]''' was founded in 1999 in the [[w:University of Southern California|University of Southern California]] by the [[w:United States Army|United States Army]]. It collaborates with the [[w:United States Army Futures Command]], [[w:United States Army Combat Capabilities Development Command]], [[w:Combat Capabilities Development Command Soldier Center]] and [[w:United States Army Research Laboratory]].

[[File:Institute for Creative Technologies (logo).jpg|thumb|right|156px|Logo of the '''[[w:Institute for Creative Technologies|Institute for Creative Technologies]]''']]

----

[[File:ESPER_LightCage.jpg|thumb|right|300px|The ESPER LightCage - 3D face scanning rig is a modern [[w:light stage|w:light stage]]]]

{{Q|A '''light stage''' or '''light cage''' is equipment used for [[w:3D modeling|shape]], [[w:texture mapping|texture]], reflectance and [[w:motion capture|motion capture]] often with [[w:structured light|structured light]] and a [[w:multi-camera setup|multi-camera setup]].|Wikipedia|[[w:light stage|light stage]]s}}

= Media forensics =

{{Q|A '''niqab''' or '''niqāb''' ("[face] veil"; also called a '''ruband''') is a garment of clothing that covers the face, worn by some [[w:muslim women|muslim women]] as a part of a particular interpretation of [[w:hijab|hijab]] (modest dress).|Wikipedia|[[w:Niqāb|Niqābs]]}}

----

= Reflectance capture =

'''Reflectance capture''' is made by measuring the reflected light for each incoming light direction and every exit direction, often with many different wavelengths. Using polarisers allow to separately capture the specular and the diffuse reflected light. The first known reflectance capture over the human face was made in 1999 by Paul Debevec et al at the [[w:University of Southern California]].

----

= Relighting =

[[File:Deb2000-relighting-low-res-cropped.png|thumb|right|420px|Each image images a face in synthesized lighting. The lower images represent the captured illumination map. The images are generated taking a dot product of each pixel’s reflectance function with the illumination map.<br /><br />

'''Relighting''' means applying a completely different [[w:lighting]] situation to an image or video which has already been imaged. As of 2020-09 the English Wikipedia does not have an article on relighting.

----

'''[[w:Spectrogram]]s''' are used extensively in the fields of [[w:music]], [[w:linguistics]], [[w:sonar]], [[w:radar]], [[w:speech processing]], [[w:seismology]], and others. Spectrograms of audio can be used to identify spoken words [[w:phonetics|phonetic]]ally, and to analyse the [[w:Animal communication|various calls of animals]]. (Wikipedia)

----

= Speech synthesis =

{{Q|'''Speech synthesis''' is the artificial production of human [[w:speech|speech]]|Wikipedia|[[w:Speech synthesis|speech syntheses]]}}

----

= Transfer learning =

{{Q|'''Transfer learning (TL)''' is a research problem in [[w:machine learning|machine learning]] (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.|Wikipedia|[[w:Transfer learning|Transfer learning]]}}

----

Please see '''[[Resources#List of voice changers]]''' for some alternatives.

----