James M. Rehg
Computer Vision and Pattern Recognition · 1999–2021
A researcher in the Science corpus: 42 papers; trusts 3,146 researchers and is trusted by 6,208 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 879 citations into it; #524 of 21,973 by trust here, #795 by citations
- Artificial Intelligence — 446 citations into it; #3,751 of 36,961 by trust here, #3,837 by citations
- Aerospace Engineering — 99 citations into it; #348 of 6,431 by trust here, #708 by citations
- Evaluation & Benchmarks — 87 citations into it
- Model Architectures — 83 citations into it; #1,731 of 2,288 by trust here, #2,225 by citations
- Signal Processing — 74 citations into it
- Representation & Self-Supervised Learning — 65 citations into it
- Human-Computer Interaction — 62 citations into it; #36 of 2,261 by trust here, #72 by citations
Whom James M. Rehg trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- David G. Lowe
- Kaiming He
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- Andrew Zisserman
- Diederik P. Kingma
- Karen Simonyan
- Yoshua Bengio
- Yann LeCun
Who trusts James M. Rehg overall
- Kristen Grauman
- Antonino Furnari
- Yin Li
- Kris M. Kitani
- Dima Damen
- Alireza Fathi
- Wenguan Wang
- Colin S. Lea
- Yong Jae Lee
- Minghuang Ma
Papers from James M. Rehg's perspective
Ordered by how strongly the researchers James M. Rehg 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
- Learning to recognize objects in egocentric activities (2011) — 633 citations
- Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021) — 1,925 citations
- Social interactions: A first-person perspective (2012) — 339 citations
- Video Segmentation by Tracking Many Figure-Ground Segments (2013) — 589 citations
- Modeling Actions through State Changes (2013) — 157 citations
- Understanding egocentric activities (2011) — 414 citations
- The Secrets of Salient Object Segmentation (2014) — 1,322 citations
- Delving into Egocentric Actions (2015) — 305 citations
- Unsupervised Learning of Edges (2015) — 99 citations
- Joint Semantic Segmentation and 3D Reconstruction from Monocular Video (2014) — 254 citations
- In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video (2018) — 395 citations
- Multiple Hypothesis Tracking Revisited (2015) — 651 citations
- A Scalable Approach to Activity Recognition based on Object Use (2007) — 399 citations
- 3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare (2018) — 359 citations
- Statistical Color Models with Application to Skin Detection (1999)
- RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions (2014) — 136 citations
- Supplementary Materials for: “Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video” (2020)
- Learning to Recognize Daily Actions Using Gaze (2012) — 444 citations
- Detecting Attended Visual Targets in Video (2020) — 167 citations
- Detection of eye contact with deep neural networks is as accurate as human experts (2020) — 60 citations