Mingli Song

Computer Vision and Pattern Recognition · 2017–2023

A researcher in the Science corpus: 18 papers; trusts 1,383 researchers and is trusted by 13 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 459 citations into it; #6,179 of 21,575 by trust here, #4,955 by citations
• Artificial Intelligence — 366 citations into it; #9,251 of 35,345 by trust here, #9,760 by citations
• Efficiency & Compression — 86 citations into it; #1,124 of 1,264 by trust here, #987 by citations
• Representation & Self-Supervised Learning — 82 citations into it
• Model Architectures — 80 citations into it
• Generative Models — 51 citations into it
• Computational Mechanics — 42 citations into it; #8,992 of 10,001 by trust here, #4,600 by citations
• Optimization & Training — 40 citations into it

Whom Mingli Song trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Kaiming He
4. Karen Simonyan
5. Yoshua Bengio
6. Diederik P. Kingma
7. Yann LeCun
8. Ilya Sutskever
9. Ross B. Girshick
10. Andrew Zisserman

Who trusts Mingli Song overall

1. Jingwen Ye
2. Lin Wang
3. Jianping Gou
4. Xinchao Wang
5. Dongze Lian
6. Yiding Yang
7. Kuk-Jin Yoon
8. Chengchao Shen
9. Yongcheng Jing
10. Baosheng Yu

Papers from Mingli Song's perspective

Ordered by how strongly the researchers Mingli Song trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. Long Short-Term Memory
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Neural Style Transfer: A Review (2017) — 870 citations
• Distilling Knowledge From Graph Convolutional Networks (2020) — 287 citations
• Learning with Recoverable Forgetting (2022) — 53 citations
• Factorizable Graph Convolutional Networks (2020) — 172 citations
• DepGraph: Towards Any Structural Pruning (2023) — 518 citations
• Meta-attention for ViT-backed Continual Learning (2022) — 66 citations
• Safe Distillation Box (2021) — 14 citations
• Amalgamating Knowledge from Heterogeneous Graph Neural Networks (2021) — 105 citations
• Collaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-talent Student Learning (2020) — 22 citations
• Progressive Network Grafting for Few-Shot Knowledge Distillation (2020) — 55 citations
• Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN (2020) — 59 citations
• Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning (2019) — 59 citations
• Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation (2019) — 65 citations
• CU-Net: Component Unmixing Network for Textile Fiber Identification (2019) — 22 citations
• Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers (2019) — 33 citations
• Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More (2019) — 86 citations
• Dynamic Instance Normalization for Arbitrary Style Transfer (2019) — 219 citations
• Amalgamating Knowledge towards Comprehensive Classification (2018) — 108 citations