most citedMulti-View Azimuth Stereo via Tangent Space Consistency

2 citations · 7 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG20231 cited

Mitigating Transformer Overconfidence via Lipschitz Regularization

Wenqian Ye, Yunsheng Ma, Xu Cao +1

Though Transformers have achieved promising results in many computer vision tasks, they tend to be over-confident in predictions, as the standard Dot Product Self-Attention (DPSA)…

cs.CV2023

CEMFormer: Learning to Predict Driver Intentions from In-Cabin and External Cameras via Spatial-Temporal Transformers

Yunsheng Ma, Wenqian Ye, Xu Cao +4

Driver intention prediction seeks to anticipate drivers' actions by analyzing their behaviors with respect to surrounding traffic environments. Existing approaches primarily focus…

cs.CV20232 cited

Multi-View Azimuth Stereo via Tangent Space Consistency

Xu Cao, Hiroaki Santo, Fumio Okura +1

We present a method for 3D reconstruction only using calibrated multi-view surface azimuth maps. Our method, multi-view azimuth stereo, is effective for textureless or specular sur…

cs.DC20232 cited

SuperScaler: Supporting Flexible DNN Parallelization via a Unified Abstraction

Zhiqi Lin, Youshan Miao, Guodong Liu +10

With the growing model size, deep neural networks (DNN) are increasingly trained over massive GPU accelerators, which demands a proper parallelization plan that transforms a DNN mo…

cs.CV20221 cited

Automatic Infectious Disease Classification Analysis with Concept Discovery

Elena Sizikova, Joshua Vendrow, Xu Cao +13

Automatic infectious disease classification from images can facilitate needed medical diagnoses. Such an approach can identify diseases, like tuberculosis, which remain under-diagn…

cs.CV20221 cited

A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimation

Yu Chen, Xu Cao, Xiaoyi Lin +4

Accurate motion and depth recovery is important for many robot vision tasks including autonomous driving. Most previous studies have achieved cooperative multi-task interaction via…