Songtao Liu
Computer Vision and Pattern Recognition · 2017–2021
A researcher in the Science corpus: 6 papers; trusts 1,277 researchers and is trusted by 32 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 227 citations into it; #4,667 of 21,575 by trust here, #3,875 by citations
- Artificial Intelligence — 116 citations into it; #9,859 of 35,345 by trust here, #7,657 by citations
- Model Architectures — 26 citations into it
- Evaluation & Benchmarks — 19 citations into it
- Optimization & Training — 13 citations into it
- Radiology, Nuclear Medicine and Imaging — 13 citations into it; #1,121 of 3,265 by trust here, #971 by citations
- Media Technology — 7 citations into it
- Efficiency & Compression — 6 citations into it
Whom Songtao Liu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Karen Simonyan
- Alex Krizhevsky
- Shaoqing Ren
- Tsung-Yi Lin
- Geoffrey E. Hinton
- Christian Szegedy
- X. Zhang
- Andrew Zisserman
Who trusts Songtao Liu overall
- Juan R. Terven
- Zheng Ge
- Chien-Yao Wang
- Diana-Margarita Córdova-Esparza
- Xingkui Zhu
- Di Huang
- Momina Liaqat Ali
- Xiaodong Cun
- Xun Cheng
- Xuangeng Chu
Papers from Songtao Liu's perspective
Ordered by how strongly the researchers Songtao Liu 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)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Receptive Field Block Net for Accurate and Fast Object Detection (2017) — 1,541 citations
- Adaptive NMS: Refining Pedestrian Detection in a Crowd (2019) — 340 citations
- YOLOX: Exceeding YOLO Series in 2021 (2021) — 6,005 citations
- Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (2020) — 363 citations
- Learning Spatial Fusion for Single-Shot Object Detection (2019) — 863 citations
- OTA: Optimal Transport Assignment for Object Detection (2021) — 529 citations