Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Bai, Shaojie"'
Autor:
Bai, Shaojie, Wang, Te-Li, Li, Chenghui, Venkatesh, Akshay, Simon, Tomas, Cao, Chen, Schwartz, Gabriel, Wrench, Ryan, Saragih, Jason, Sheikh, Yaser, Wei, Shih-En
Publikováno v:
ACM Trans. Graph. 43, 4, Article 93 (July 2024), 22 pages.
Faithful real-time facial animation is essential for avatar-mediated telepresence in Virtual Reality (VR). To emulate authentic communication, avatar animation needs to be efficient and accurate: able to capture both extreme and subtle expressions wi
Externí odkaz:
http://arxiv.org/abs/2407.13038
Virtual Reality (VR) bares promise of social interactions that can feel more immersive than other media. Key to this is the ability to accurately animate a personalized photorealistic avatar, and hence the acquisition of the labels for headset-mounte
Externí odkaz:
http://arxiv.org/abs/2401.11002
Autor:
Ng, Evonne, Romero, Javier, Bagautdinov, Timur, Bai, Shaojie, Darrell, Trevor, Kanazawa, Angjoo, Richard, Alexander
We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction. Given speech audio, we output multiple possibilities of gestural motion for an individual, includi
Externí odkaz:
http://arxiv.org/abs/2401.01885
Autor:
Anil, Cem, Pokle, Ashwini, Liang, Kaiqu, Treutlein, Johannes, Wu, Yuhuai, Bai, Shaojie, Kolter, Zico, Grosse, Roger
Designing networks capable of attaining better performance with an increased inference budget is important to facilitate generalization to harder problem instances. Recent efforts have shown promising results in this direction by making use of depth-
Externí odkaz:
http://arxiv.org/abs/2211.09961
Weighted Majority Voting (WMV) is a well-known optimal decision rule for collective decision making, given the probability of sources to provide accurate information (trustworthiness). However, in reality, the trustworthiness is not a known quantity
Externí odkaz:
http://arxiv.org/abs/2207.06118
Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a stable flow estimation. However, these RNNs impose large computation a
Externí odkaz:
http://arxiv.org/abs/2204.08442
Publikováno v:
Neurips 2021
Many tasks in deep learning involve optimizing over the \emph{inputs} to a network to minimize or maximize some objective; examples include optimization over latent spaces in a generative model to match a target image, or adversarially perturbing an
Externí odkaz:
http://arxiv.org/abs/2111.13236
This paper focuses on training implicit models of infinite layers. Specifically, previous works employ implicit differentiation and solve the exact gradient for the backward propagation. However, is it necessary to compute such an exact but expensive
Externí odkaz:
http://arxiv.org/abs/2111.05177
Autor:
Du, Linkang, Zhang, Zhikun, Bai, Shaojie, Liu, Changchang, Ji, Shouling, Cheng, Peng, Chen, Jiming
For protecting users' private data, local differential privacy (LDP) has been leveraged to provide the privacy-preserving range query, thus supporting further statistical analysis. However, existing LDP-based range query approaches are limited by the
Externí odkaz:
http://arxiv.org/abs/2110.07505
Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer. These models have been shown to achieve performance competitive with the state-of-the-art deep
Externí odkaz:
http://arxiv.org/abs/2106.14342