Li-Jia Li
Computer Vision and Pattern Recognition · 2007–2019
A researcher in the Science corpus: 27 papers; trusts 2,867 researchers and is trusted by 19,888 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 725 citations into it; #47 of 21,973 by trust here, #39 by citations
- Artificial Intelligence — 531 citations into it; #2,420 of 36,961 by trust here, #1,508 by citations
- Natural Language Processing — 101 citations into it
- Evaluation & Benchmarks — 91 citations into it; #10 of 3,155 by trust here, #3 by citations
- Optimization & Training — 76 citations into it; #775 of 2,605 by trust here, #428 by citations
- Model Architectures — 75 citations into it; #896 of 2,288 by trust here, #302 by citations
- Representation & Self-Supervised Learning — 72 citations into it; #2,785 of 3,156 by trust here, #2,367 by citations
- Multimodal Learning — 69 citations into it; #163 of 1,215 by trust here, #56 by citations
Whom Li-Jia Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- David G. Lowe
- Li Fei-Fei
- Alex Krizhevsky
- Rob Fergus
- Geoffrey E. Hinton
- Kaiming He
- Andrew Zisserman
- Ross B. Girshick
- Antonio Torralba
- Yoshua Bengio
Who trusts Li-Jia Li overall
- Li Fei-Fei
- Kristen Grauman
- Trevor Darrell
- Abhinav Kumar Gupta
- Yoshua Bengio
- Yi Yang
- Xinlei Chen
- Antonio Torralba
- Andrea Vedaldi
- Kaiming He
Papers from Li-Jia Li's perspective
Ordered by how strongly the researchers Li-Jia Li 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
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- ImageNet: A large-scale hierarchical image database (2009) — 74,730 citations
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016) — 6,638 citations
- Progressive Neural Architecture Search (2017) — 2,159 citations
- Image retrieval using scene graphs (2015) — 1,234 citations
- Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification (2010) — 1,082 citations
- The New Data and New Challenges in Multimedia Research (2015) — 332 citations
- What, where and who? Classifying events by scene and object recognition (2007) — 864 citations
- Towards total scene understanding: Classification, annotation and segmentation in an automatic framework (2009) — 565 citations
- OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning (2007) — 494 citations
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices (2018) — 1,502 citations
- Iterative Visual Reasoning Beyond Convolutions (2018) — 225 citations
- Best of both worlds: Human-machine collaboration for object annotation (2015) — 219 citations
- Co-localization in Real-World Images (2014) — 199 citations
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels (2017) — 1,683 citations
- Learning from Noisy Labels with Distillation (2017) — 593 citations
- Deep Reinforcement Learning-Based Image Captioning with Embedding Reward (2017) — 339 citations
- Multi-view Face Detection Using Deep Convolutional Neural Networks (2015) — 593 citations
- Getting the look: clothing recognition and segmentation for automatic product suggestions in everyday photos (2013) — 199 citations
- Learning Features and Parts for Fine-Grained Recognition (2014) — 124 citations
- MentorNet: Regularizing Very Deep Neural Networks on Corrupted Labels (2017) — 83 citations