Ji Lin
Computer Vision and Pattern Recognition · 2007–2023
A researcher in the Science corpus: 23 papers; trusts 2,777 researchers and is trusted by 1,879 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 706 citations into it; #1,299 of 21,973 by trust here, #1,230 by citations
- Artificial Intelligence — 628 citations into it; #4,218 of 36,961 by trust here, #2,592 by citations
- Efficiency & Compression — 247 citations into it; #112 of 1,273 by trust here, #87 by citations
- Model Architectures — 127 citations into it
- Evaluation & Benchmarks — 96 citations into it
- Large Language Models — 93 citations into it; #645 of 810 by trust here, #530 by citations
- Optimization & Training — 67 citations into it
- Generative Models — 63 citations into it; #1,495 of 1,963 by trust here, #976 by citations
Whom Ji Lin trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Ross B. Girshick
- Yoshua Bengio
- Diederik P. Kingma
- Christian Szegedy
- Yann LeCun
- Ilya Sutskever
- Karen Simonyan
Who trusts Ji Lin overall
- Christoph Feichtenhofer
- Song Han
- Jonathan Munro
- Emmanuel Kahembwe
- Hengduo Li
- Limin Wang
- Zhijian Liu
- Rameswar Panda
- Yihui He
- Chaoxia Wu
Papers from Ji Lin's perspective
Ordered by how strongly the researchers Ji Lin 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
- TSM: Temporal Shift Module for Efficient Video Understanding (2018) — 2,128 citations
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices (2018) — 1,502 citations
- Runtime Neural Pruning (2017) — 528 citations
- Reinforcement Learning from Imperfect Demonstrations (2018) — 211 citations
- Differentiable Augmentation for Data-Efficient GAN Training (2020) — 694 citations
- HAQ: Hardware-Aware Automated Quantization With Mixed Precision (2018) — 1,120 citations
- Temporal Shift Module for Efficient Video Understanding (2018) — 221 citations
- Lite Transformer with Long-Short Range Attention (2020) — 392 citations
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models (2022) — 1,734 citations
- Joint Monocular 3D Vehicle Detection and Tracking (2018) — 246 citations
- VILA: On Pre-training for Visual Language Models (2023) — 896 citations
- Defensive Quantization: When Efficiency Meets Robustness (2019) — 222 citations
- Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution (2020) — 863 citations
- AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration (2023) — 1,557 citations
- MCUNet: Tiny Deep Learning on IoT Devices (2020) — 741 citations
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration (2023) — 857 citations
- Spectral gradient projection method for monotone nonlinear equations with convex constraints (2009) — 161 citations
- On-Device Training Under 256KB Memory (2022) — 317 citations
- GAN Compression: Efficient Architectures for Interactive Conditional GANs (2020) — 241 citations
- HAQ: Hardware-Aware Automated Quantization (2018) — 101 citations