Limin Wang
Computer Vision and Pattern Recognition · 2012–2024
A researcher in the Science corpus: 39 papers; trusts 3,837 researchers and is trusted by 7,881 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,586 citations into it; #385 of 21,973 by trust here, #527 by citations
- Artificial Intelligence — 934 citations into it; #2,391 of 36,961 by trust here, #2,613 by citations
- Evaluation & Benchmarks — 212 citations into it
- Model Architectures — 206 citations into it; #837 of 2,288 by trust here, #1,149 by citations
- Multimodal Learning — 198 citations into it; #841 of 1,215 by trust here, #1,037 by citations
- Representation & Self-Supervised Learning — 159 citations into it; #2,434 of 3,156 by trust here, #2,568 by citations
- Large Language Models — 80 citations into it
- Biomedical Engineering — 66 citations into it
Whom Limin Wang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Karen Simonyan
- Kaiming He
- Alex Krizhevsky
- Ross B. Girshick
- Andrew Zisserman
- Geoffrey E. Hinton
- Christian Szegedy
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
Who trusts Limin Wang overall
- Yu Qiao
- Christoph Feichtenhofer
- Luc Van Gool
- Yuanjun Xiong
- Ali Diba
- Rohit Girdhar
- Xiaoou Tang
- Cordelia Schmid
- Kunchang Li
- X. Wang
Papers from Limin Wang's perspective
Ordered by how strongly the researchers Limin Wang trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (2016) — 4,303 citations
- Action recognition with trajectory-pooled deep-convolutional descriptors (2015) — 1,199 citations
- Towards Good Practices for Very Deep Two-Stream ConvNets (2015) — 463 citations
- Temporal Action Detection with Structured Segment Networks (2017) — 982 citations
- UntrimmedNets for Weakly Supervised Action Recognition and Detection (2017) — 522 citations
- VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training (2022) — 2,096 citations
- Real-Time Action Recognition with Enhanced Motion Vector CNNs (2016) — 439 citations
- Video Action Detection with Relational Dynamic-Poselets (2014) — 138 citations
- Learning Spatiotemporal Features via Video and Text Pair Discrimination (2020) — 64 citations
- Actionness Estimation Using Hybrid Fully Convolutional Networks (2016) — 104 citations
- Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice (2014) — 616 citations
- Motionlets: Mid-level 3D Parts for Human Motion Recognition (2013) — 162 citations
- Appearance-and-Relation Networks for Video Classification (2017) — 376 citations
- Temporal Segment Networks for Action Recognition in Videos (2017) — 969 citations
- VideoChat: chat-centric video understanding (2023) — 975 citations
- WebVision Database: Visual Learning and Understanding from Web Data (2017) — 515 citations
- TEA: Temporal Excitation and Aggregation for Action Recognition (2020) — 566 citations
- Mining Motion Atoms and Phrases for Complex Action Recognition (2013) — 90 citations
- InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation (2023) — 513 citations
- Multi-view Super Vector for Action Recognition (2014) — 202 citations