Shih-Fu Chang
Computer Vision and Pattern Recognition · International Conference on Machine Learning · 1999–2022
A researcher in the Science corpus: 57 papers; trusts 3,906 researchers and is trusted by 5,537 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,301 citations into it; #564 of 21,973 by trust here, #691 by citations
- Artificial Intelligence — 973 citations into it; #2,169 of 36,961 by trust here, #2,063 by citations
- Representation & Self-Supervised Learning — 289 citations into it; #1,353 of 3,156 by trust here, #736 by citations
- Multimodal Learning — 195 citations into it; #555 of 1,215 by trust here, #400 by citations
- Natural Language Processing — 176 citations into it
- Evaluation & Benchmarks — 132 citations into it
- Model Architectures — 131 citations into it; #397 of 2,288 by trust here, #731 by citations
- Signal Processing — 85 citations into it; #4,901 of 7,592 by trust here, #920 by citations
Whom Shih-Fu Chang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Ross B. Girshick
- David G. Lowe
- Yoshua Bengio
- Diederik P. Kingma
- Karen Simonyan
- Ilya Sutskever
- Andrew Zisserman
Who trusts Shih-Fu Chang overall
- Wei David Liu
- Jingdong Wang
- Jun Wang
- Fumin Shen
- Wu-Jun Li
- Kaiming He
- Mingsheng Long
- Jingkuan Song
- Cheng Deng
- Chunhua Shen
Papers from Shih-Fu Chang's perspective
Ordered by how strongly the researchers Shih-Fu Chang 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
- 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
- Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs (2016) — 973 citations
- Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019) — 642 citations
- VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text (2021) — 756 citations
- Open-Vocabulary Object Detection Using Captions (2020) — 613 citations
- ConvNet Architecture Search for Spatiotemporal Feature Learning (2017) — 417 citations
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos (2017) — 586 citations
- Large-scale concept ontology for multimedia (2006) — 750 citations
- Semi-supervised hashing for scalable image retrieval (2010) — 656 citations
- Designing Category-Level Attributes for Discriminative Visual Recognition (2013) — 220 citations
- Supervised hashing with kernels (2012) — 1,483 citations
- Detecting and Simulating Artifacts in GAN Fake Images (2019) — 652 citations
- Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks (2015) — 384 citations
- Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks (2017) — 236 citations
- An Exploration of Parameter Redundancy in Deep Networks with Circulant Projections (2015) — 341 citations
- Semi-Supervised Hashing for Large-Scale Search (2012) — 814 citations
- Learning to Hash for Indexing Big Data—A Survey (2015) — 546 citations
- VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs (2021) — 78 citations
- Consumer video understanding: a benchmark database and an evaluation of human and machine performance (2011) — 359 citations
- Large-scale visual sentiment ontology and detectors using adjective noun pairs (2013) — 850 citations
- Cross-domain learning methods for high-level visual concept classification (2008) — 186 citations