A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Unsupervised Generation of Free-Form and Parameterized Avatars
2018
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
We compare the two unsupervised learning problems to the problem of unsupervised domain adaptation, define generalization bounds that are based on discrepancy, and employ a GAN to implement network solutions ...
In both cases, no supervision is given during training in the form of matching inputs and outputs. ...
NETWORKS FOR FREE-FORM GENERATION We next reformulate the problems as neural network challenges. ...
doi:10.1109/tpami.2018.2863282
pmid:30080143
fatcat:hj4d345gxbh2fliixwxidacaja
AVATAR: AI Vision Analysis for Three-dimensional Action in Real-time
[article]
2022
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Artificial intelligence (AI) is an emerging tool for high-resolution behavioural analysis and conduction of human-free behavioural experiments. ...
Here, we applied an AI-based system, AVATAR, which automatically virtualises 3D motions from the detection of 9 body parts. ...
These results suggest that the AVATAR system can be useful for unsupervised characterization and quantification of motion and action sequences. ...
doi:10.1101/2021.12.31.474634
fatcat:ol45gwbspfdalk25gius7mynu4
Unsupervised Control Through Non-Parametric Discriminative Rewards
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. ...
We demonstrate the efficacy of our agent to learn, in an unsupervised manner, to reach a diverse set of goals on three domains -- Atari, the DeepMind Control Suite and DeepMind Lab. ...
Machado, Will Dabney, Hado van Hasselt, and anonymous reviewers for useful feedback on drafts of the manuscript. ...
arXiv:1811.11359v1
fatcat:ytbyfennwrakfm753umn5ofzwe
Let's face it: Probabilistic multi-modal interlocutor-aware generation of facial gestures in dyadic settings
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
One key aspect of this is generation of appropriate non-verbal behavior for the agent, for example facial gestures, here defined as facial expressions and head movements. ...
and speech articulation in a 3D avatar; b) an extension to MoGlow, a recent motion-synthesis method based on normalizing flows, to also take multi-modal signals from the interlocutor as input and subsequently ...
Finally, there must be a fully automatic process for analyzing video and synthesizing 3D avatars that allows unsupervised processing of several hours of video from different talkers. ...
arXiv:2006.09888v1
fatcat:i3v7cfl4tzgmzgpuboiktr66tq
User Experience Sensor for Man–Machine Interaction Modeled as an Analogy to the Tower of Hanoi
2020
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The HINT system, defined as a combination of an extensive AI system and the possibility of attaching a human expert, is designed to be used by relational agents, which may have a physical form, such as ...
The proposed sensor evaluates the user experience and measures the user/employee efficiency at every stage of a given process, offering the user to choose other forms of information, interaction, or expert ...
Conflicts of Interest: The authors declare no conflict of interest.
Abbreviations The following abbreviations are used in this manuscript: ...
doi:10.3390/s20154074
pmid:32707823
pmcid:PMC7435367
fatcat:yfmje3ytmneolao3avrhs237ri
Automated Face Analysis for Affective Computing
[chapter]
2015
The Oxford Handbook of Affective Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Automated Face Analysis (AFA) for detection, synthesis, and understanding of facial expression is a vital focus of basic research. ...
action unit and intensity detection, physical pain, psychological distress and depression, detection of deception, interpersonal coordination, expression transfer, and other applications. ...
The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH or ARL. ...
doi:10.1093/oxfordhb/9780199942237.013.020
fatcat:qrhzadx6y5bxzjo6nnfshhwoze
FENeRF: Face Editing in Neural Radiance Fields
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our experiments demonstrate that FENeRF outperforms state-of-the-art methods in various face editing tasks. ...
Moreover, we reveal that joint learning semantics and texture helps to generate finer geometry. ...
Discriminators In order to learn the unsupervised 3D representations, we design two discriminators D c and D s both of which are parameterized as CNN with leaky ReLU activation [20] . ...
arXiv:2111.15490v2
fatcat:qtqaijbwhncn7g3ncwjraehr6q
A Metaverse: taxonomy, components, applications, and open challenges
2022
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Unlike previous studies on the Metaverse based on Second Life, the current Metaverse is based on the social value of Generation Z that online and offline selves are not different. ...
With the technological development of deep learning-based high-precision recognition models and natural generation models, Metaverse is being strengthened with various factors, from mobile-based always-on ...
For example, in the drama Westworld, avatars perform various actions in the Metaverse, freeing from the constraints and conditions of reality. ...
doi:10.1109/access.2021.3140175
fatcat:fnraeaz74vh33knfvhzrynesli
Unsupervised text mining methods for literature analysis: a case study for Thomas Pynchon's V
2013
Orbit : Writing Around Pynchon
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Unsupervised text mining methods for literature analysis: a case study for Thomas Pynchon's V. ...
work presented herein; and Markus Hofmann, for fruitful remarks on a late draft of this work. ...
Also, active support and encouragement by all colleagues of the 9th Training Group / 10th Training Cohort of the Supreme Joint War College is gratefully acknowledged. ...
doi:10.7766/orbit.v1.2.44
fatcat:7oioosyulza73cug7bu4cx7aau
Realistic One-shot Mesh-based Head Avatars
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The resulting avatars are rigged and can be rendered using a neural network, which is trained alongside the mesh and texture estimators on a dataset of in-the-wild videos. ...
In the experiments, we observe that our system performs competitively both in terms of head geometry recovery and the quality of renders, especially for the cross-person reenactment. ...
We also thank Arsenii Ashukha for their comments and suggestions regarding the text contents and clarity, as well as Julia Churkina for helping us with proof-reading. ...
arXiv:2206.08343v1
fatcat:oulmepan55gcxly4niomcuxezi
Learning more skills through optimistic exploration
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Unsupervised skill learning objectives (Gregor et al., 2016, Eysenbach et al., 2018) allow agents to learn rich repertoires of behavior in the absence of extrinsic rewards. ...
classifications, leading to low intrinsic reward for the agent and effective penalization of the sort of exploration needed to actually maximize the objective. ...
and plotting, Phil Bachman for correcting the error discussed in Appendix C, and David Schwab for pointing us to the original Query by Committee work (Seung et al., 1992) . ...
arXiv:2107.14226v6
fatcat:ybh2q3ldqfgjpmrcsy7oxbqzau
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. ...
Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness. ...
Acknowledgments We would like to thank Matt Botvinick, Tiago Ramalho, Tejas Kulkarni, and Csaba Szepesvari for helpful discussions and insights. ...
arXiv:1905.09275v2
fatcat:gvkoisskqnadvghggtc7i3xnxy
HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We demonstrate that hybrid rendering enables HVTR to handle complicated motions, render high-quality avatars under user-controlled poses/shapes and even loose clothing, and most importantly, be fast at ...
The key advantage of our approach is that we can then convert the fused features into a high resolution, high-quality avatar by a fast GAN-based textural renderer. ...
form of renderings of a skeleton [4, 60, 53, 24, 79, 69],
skirts (Fig. 5). ...
arXiv:2112.10203v1
fatcat:fypyninknbfopb73m343dmeoua
Topologically Consistent Multi-View Face Inference Using Volumetric Sampling
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
ToFu further captures displacement maps for pore-level geometric details and facilitates high-quality rendering in the form of albedo and specular reflectance maps. ...
Our novel progressive mesh generation network embeds the topological structure of the face in a feature volume, sampled from geometry-aware local features. ...
high-quality facial appearance in form of albedo and spec-
mesh reconstruction [22]). ...
arXiv:2110.02948v1
fatcat:d6be6b66jneotjjco4ybkj2lym
State of the Art on Neural Rendering
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
free-viewpoint video, and the creation of photo-realistic avatars for virtual and augmented reality telepresence. ...
However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo-realistic computer graphics more widely accessible ...
The domain gap between rendered avatars and headset images is closed by using unsupervised image-to-image translation techniques. ...
arXiv:2004.03805v1
fatcat:6qs7ddftkfbotdlfd4ks7llovq
« Previous
Showing results 1 — 15 out of 165 results