2009 · 2009 IEEE Conference on Computer Vision and Pattern Recognition
ImageNet: A large-scale hierarchical image database
63,487 citationsRead
Most cited
133 papers in total2015 · International Journal of Computer Vision
ImageNet Large Scale Visual Recognition Challenge
40,733 citationsRead
2016 · Lecture notes in computer science
Stacked Hourglass Networks for Human Pose Estimation
5,296 citationsRead
2018 · Lecture notes in computer science
CornerNet: Detecting Objects as Paired Keypoints
3,620 citationsRead
2013
3D Object Representations for Fine-Grained Categorization
3,595 citationsRead
2020 · Lecture notes in computer science
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2,602 citationsRead
Newest first
133 papers in total2025
- WAFT: Warping-Alone Field Transforms for Optical FlowarXiv (Cornell University) · 1 citations
- Mesh Extraction for Unbounded Scenes Using Camera-Aware Octrees1 citations
- Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees1 citations
- Improvement of finescale parameterization through reducing uncertainty in spectrum estimationDynamics of Atmospheres and Oceans
- Diagnostic value of 18F-FDG and 68Ga-FAPI in head and neck cancers: A systematic review and meta-analysis.PubMed
- The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning
- YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model
- What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?arXiv (Cornell University)
2024
- SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical FlowLecture notes in computer science · 73 citations
- Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation43 citations
- OGNI-DC: Robust Depth Completion with Optimization-Guided Neural IterationsLecture notes in computer science · 17 citations
- LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-layer Optical FlowLecture notes in computer science · 3 citations
- YuLan-Mini: An Open Data-efficient Language ModelarXiv (Cornell University)
2023
- Infinite Photorealistic Worlds Using Procedural Generation77 citations
- Disentangled representation transformer network for 3D face reconstruction and robust dense alignmentThe Visual Computer · 12 citations
- Convolutional Networks with Oriented 1D Kernels7 citations
- Deformable Feature Interaction Network and Graph Structure Reasoning for 3D Dense Alignment and Face Reconstruction6 citations
- View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic DataarXiv (Cornell University)
2022
- Multiview Stereo with Cascaded Epipolar RAFTLecture notes in computer science · 40 citations
2021
- RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching2021 International Conference on 3D Vision (3DV) · 528 citations
- RAFT-3D: Scene Flow using Rigid-Motion Embeddings122 citations
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (Extended Abstract)108 citations
- A Study of Face Obfuscation in ImageNetarXiv (Cornell University) · 66 citations
- Dynamically Grown Generative Adversarial NetworksProceedings of the AAAI Conference on Artificial Intelligence · 13 citations
- Non-deep NetworksarXiv (Cornell University) · 1 citations
2020
- Towards fairer datasets230 citations
- D3D: Distilled 3D Networks for Video Action Recognition158 citations
- How Useful Is Self-Supervised Pretraining for Visual Tasks?123 citations
Research in numbers
From OpenAlex- conference paper60
- preprint49
- article24
- arXiv (Cornell University)49
- Lecture notes in computer science12
- Applied Mechanics and Materials4
- International Journal of Computer Vision3
- Proceedings of the AAAI Conference on Artificial Intelligence3
- Li Fei-Fei25
- Jonathan Krause15
- Kaiyu Yang12
- Olga Russakovsky11
- Hei Law10
Experience and education
Universities
2007 to 2025Princeton University
2023Ningxia Normal University
2014 to 2019University of Michigan
2013 to 2014Beijing Institute of Technology
Industry and labs
2025Ministry of Natural Resources
2025Numerical Method (China)
2025First Institute of Oceanography
2014 to 2020Google (United States)
2017Ann Arbor Center for Independent Living
2016 to 2017Robotics Research (United States)