Harry Shum
Computer Vision and Pattern Recognition · 2000–2025
A researcher in the Science corpus: 35 papers; trusts 1,214 researchers and is trusted by 6,271 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 366 citations into it; #519 of 21,973 by trust here, #966 by citations
- Artificial Intelligence — 242 citations into it; #8,966 of 36,961 by trust here, #6,235 by citations
- Natural Language Processing — 102 citations into it; #1,846 of 5,725 by trust here, #2,216 by citations
- Computer Graphics and Computer-Aided Design — 79 citations into it; #182 of 1,641 by trust here, #151 by citations
- Computational Mechanics — 45 citations into it; #1,947 of 10,021 by trust here, #688 by citations
- Evaluation & Benchmarks — 35 citations into it
- Large Language Models — 35 citations into it
- Model Architectures — 34 citations into it; #2,170 of 2,288 by trust here, #1,052 by citations
Whom Harry Shum trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- William T. Freeman
- Yoshua Bengio
- Oriol Vinyals
- Kaiming He
- Alex Krizhevsky
- Ilya Sutskever
- Diederik P. Kingma
- Yann LeCun
- Yuri Boykov
Who trusts Harry Shum overall
- Ce Liu
- Qingxiong Yang
- Kaiming He
- Jianfeng Gao
- Xiaogang Wang
- Daniel Scharstein
- Olga Veksler
- Vladimir Kolmogorov
- Heiko Hirschmüller
- C. Lawrence Zitnick
Papers from Harry Shum's perspective
Ordered by how strongly the researchers Harry Shum 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- 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 Detect A Salient Object (2007) — 2,609 citations
- Lazy snapping (2004) — 1,278 citations
- Stereo Matching Using Belief Propagation (2002) — 1,637 citations
- Image super-resolution using gradient profile prior (2008) — 1,020 citations
- Real-time texture synthesis by patch-based sampling (2001) — 769 citations
- The Design and Implementation of XiaoIce, an Empathetic Social Chatbot (2018) — 748 citations
- Statistical Learning of Multi-view Face Detection (2002) — 473 citations
- Motion texture: a two-level statistical model for character motion synthesis (2002) — 515 citations
- Image completion with structure propagation (2005) — 666 citations
- Efficient indexing for large scale visual search (2009) — 61 citations
- Face Hallucination: Theory and Practice (2007) — 437 citations
- Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation (2022) — 638 citations
- DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection (2022) — 2,919 citations
- From Eliza to XiaoIce: challenges and opportunities with social chatbots (2018) — 633 citations
- Image hallucination with primal sketch priors (2003) — 435 citations
- A two-step approach to hallucinating faces: global parametric model and local nonparametric model (2001) — 384 citations
- Paint selection (2009) — 137 citations
- Review of image-based rendering techniques (2000) — 477 citations
- Full-frame video stabilization with motion inpainting (2006) — 604 citations
- Plenoptic sampling (2000) — 781 citations