Heng Wang
Computer Vision and Pattern Recognition · with Tran · 2009–2022
A researcher in the Science corpus: 12 papers; trusts 2,233 researchers and is trusted by 7,002 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 490 citations into it; #456 of 21,973 by trust here, #770 by citations
- Artificial Intelligence — 219 citations into it; #1,375 of 36,961 by trust here, #1,400 by citations
- Evaluation & Benchmarks — 56 citations into it; #1,009 of 3,155 by trust here, #713 by citations
- Model Architectures — 46 citations into it; #643 of 2,288 by trust here, #780 by citations
- Representation & Self-Supervised Learning — 32 citations into it
- Media Technology — 21 citations into it
- Optimization & Training — 18 citations into it
- Aerospace Engineering — 17 citations into it
Whom Heng Wang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ivan Laptev
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- David G. Lowe
- Cordelia Schmid
- Andrew Zisserman
- Yoshua Bengio
- Piotr Doll'ar
Who trusts Heng Wang overall
- Chen Sun
- Limin Wang
- Hossein Rahmani
- Rohit Girdhar
- Yu Kong
- Cordelia Schmid
- Marcus Rohrbach
- Andrew Zisserman
- Yi Yang
- Du Tran
Papers from Heng Wang's perspective
Ordered by how strongly the researchers Heng Wang trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Action recognition by dense trajectories (2011) — 2,386 citations
- Evaluation of Local Spatio-temporal Features for Action Recognition (2009) — 1,506 citations
- A Closer Look at Spatiotemporal Convolutions for Action Recognition (2017) — 3,656 citations
- Dense Trajectories and Motion Boundary Descriptors for Action Recognition (2013) — 1,794 citations
- Is Space-Time Attention All You Need for Video Understanding? (2021) — 3,167 citations
- Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition (2019) — 319 citations
- Video Classification With Channel-Separated Convolutional Networks (2019) — 655 citations
- SLAC: A Sparsely Labeled Dataset for Action Classification and Localization (2017) — 31 citations
- Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation (2021) — 157 citations
- A Robust and Efficient Video Representation for Action Recognition (2015) — 339 citations
- Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity (2022) — 56 citations
- LEAR-INRIA submission for the THUMOS workshop (2013)