Tong Lu
Computer Vision and Pattern Recognition · 2018–2025
A researcher in the Science corpus: 21 papers; trusts 1,725 researchers and is trusted by 87 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,015 citations into it; #3,402 of 21,575 by trust here, #1,260 by citations
- Artificial Intelligence — 714 citations into it; #15,727 of 35,345 by trust here, #2,604 by citations
- Model Architectures — 199 citations into it; #1,393 of 2,278 by trust here, #367 by citations
- Evaluation & Benchmarks — 151 citations into it
- Natural Language Processing — 66 citations into it
- Optimization & Training — 61 citations into it
- Representation & Self-Supervised Learning — 57 citations into it
- Media Technology — 53 citations into it
Whom Tong Lu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- Karen Simonyan
- Yoshua Bengio
- Yann LeCun
- Ilya Sutskever
- Diederik P. Kingma
- Christian Szegedy
Who trusts Tong Lu overall
Papers from Tong Lu's perspective
Ordered by how strongly the researchers Tong Lu 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (2021) — 5,140 citations
- Vision Transformer Adapter for Dense Predictions (2022) — 888 citations
- PVT v2: Improved baselines with Pyramid Vision Transformer (2021) — 2,512 citations
- VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks (2023) — 699 citations
- Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers (2021) — 191 citations
- InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions (2022) — 1,149 citations
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks (2023) — 3,154 citations
- Shape Robust Text Detection With Progressive Scale Expansion Network (2018) — 722 citations
- Panoptic SegFormer (2021)
- TAM: Temporal Adaptive Module for Video Recognition (2020) — 374 citations
- How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites (2024) — 1,231 citations
- Dynamic Sampling Networks for Efficient Action Recognition in Videos (2020) — 85 citations
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency (2025) — 1,136 citations
- BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers (2024) — 491 citations
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling (2024) — 1,631 citations
- Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation (2022) — 46 citations
- BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (2022) — 1,985 citations
- Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method (2022) — 654 citations
- A novel forget-update module for few-shot domain generalization (2022) — 13 citations
- ARNet: Active-Reference Network for Few-Shot Image Semantic Segmentation (2021) — 7 citations