activity
20152026
most citedAttentional Pooling for Action Recognition

209 citations · 919 across the 46 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.CV202152 cited

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

Jason Y. Zhang, Gengshan Yang, Shubham Tulsiani +1

Recent history has seen a tremendous growth of work exploring implicit representations of geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works are f…

cs.CV2021

Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories

Fait Poms, Vishnu Sarukkai, Ravi Teja Mullapudi +4

For machine learning models trained with limited labeled training data, validation stands to become the main bottleneck to reducing overall annotation costs. We propose a statistic…

cs.CV2021

FOVEA: Foveated Image Magnification for Autonomous Navigation

Chittesh Thavamani, Mengtian Li, Nicolas Cebron +1

Efficient processing of high-res video streams is safety-critical for many robotics applications such as autonomous driving. To maintain real-time performance, many practical syste…

cs.CV2021

LASR: Learning Articulated Shape Reconstruction from a Monocular Video

Gengshan Yang, Deqing Sun, Varun Jampani +6

Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structur…

cs.CV20212 cited

Streaming Self-Training via Domain-Agnostic Unlabeled Images

Zhiqiu Lin, Deva Ramanan, Aayush Bansal

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on t…

cs.CV2021

OpenGAN: Open-Set Recognition via Open Data Generation

Shu Kong, Deva Ramanan

Real-world machine learning systems need to analyze test data that may differ from training data. In K-way classification, this is crisply formulated as open-set recognition, core…