Dahua Lin

43.4k citations

201 papers · 15.8k indexed · 13 hit papers · h-index 50

Impact in

Computer Vision and Pattern Recognition top 0.02%
- Human Pose and Action Recognition
- Advanced Neural Network Applications
- Multimodal Machine Learning Applications
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
Artificial Intelligence top 0.05%
- Domain Adaptation and Few-Shot Learning
- Anomaly Detection Techniques and Applications

Papers in

Computer Vision and Pattern Recognition 142
- Advanced Neural Network Applications 35
- Human Pose and Action Recognition 32
- Multimodal Machine Learning Applications 32
- Advanced Vision and Imaging 31
- Advanced Image and Video Retrieval Techniques 31
- Video Analysis and Summarization 19
Computer Graphics and Computer-Aided Design 14

Co-authors: Yuanjun Xiong Sijie Yan Stella X. Yu Zhirong Wu Chen Change Loy Kai Chen Jiangmiao Pang Bo Dai
Journals: IEEE Transactions on Pattern Analysis and Machine Intelligence (7 papers)International Journal of Computer Vision (5 papers)IEEE Transactions on Multimedia (4 papers)ACM Transactions on Graphics (3 papers)Neurocomputing (1 paper)
Partner nations: Hong Kong China United States

In The Last Decade

Dahua Lin

181 papers receiving 15.4k citations

Hit Papers

13 papers align trajectories log scale

VBench: Comprehensive Benchmark Suite for Video Generative Models 2024 · 56 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2024 VBench: Comprehensive Benchmark Suite for Video Generative Models
2024 Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
2022 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2021 Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
2021 FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
2019 Learning a Unified Classifier Incrementally via Rebalancing
2019 CARAFE: Content-Aware ReAssembly of FEatures
2019 Region Proposal by Guided Anchoring
2019 Libra R-CNN: Towards Balanced Learning for Object Detection
2018 Proceedings of the AAAI Conference on Artificial Intelligence
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence
2018 Unsupervised Feature Learning via Non-parametric Instance Discrimination
2017 UntrimmedNets for Weakly Supervised Action Recognition and Detection

Peers

Countries citing papers authored by Dahua Lin

Since Specialization

Citations

This map shows the geographic impact of Dahua Lin's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Dahua Lin with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Dahua Lin more than expected).

Fields of papers citing papers by Dahua Lin

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Dahua Lin. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Dahua Lin. The network helps show where Dahua Lin may publish in the future.

Co-authors

The 25 scholars most cited alongside Dahua Lin, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Dahua Lin Line = papers co-authored together Dahua Lin links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work
1	GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation Zhan-zhuang ZENG, О. В. Гефнер, Mar Gutiérrez-Lobón, Zichao Ma, J. J. Song, Feiming Bai, Dahua Lin, Lijun Wu, Lance Evans	2025	0
2	AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views ACM Transactions on Graphics ·Sven Friderich, Mehrdad Ashrafi, Linning Xu, Tao Lu, A.H. Timmer, Saioa Gartzia Agirre, Z. Zhang, Aline Thomazini Cordeiro, Jiangmiao Pang, Feng Zhao, Dahua Lin, Bo Dai	2025	0
3	LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation DR-NTU (Nanyang Technological University) ·timoteus Nusan, Oliveros Alejandro, Haitami, Tong Wu, Gordon Wetzstein, Ziwei Liu, Dahua Lin	2025	4
4	Navigating the OverKill in Large Language Models Chenyu Shi, Xiao Wang, 尚司池内, Wang Haoqi, Kan Xinglong, Tao Gui, Qi Zhang, Xuanjing Huang, Pat B. Hillyard, Dahua Lin	2024	1
5	ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs Mitsuru Isobe, Dmytro D. Yaremkevich, Child Prostitution, E. A. Eeley, Dahua Lin, Kai Chen	2024	12
6	Balanced Data Sampling for Language Model Training with Clustering Yunfan Shao, Linyang Li, 昌夫清水, Hang Yan, Dahua Lin, Xipeng Qiu	2024	0
7	Identifying Semantic Induction Heads to Understand In-Context Learning Jie Ren, Qipeng Guo, Hang Yan, 憲郎村上, Quanshi Zhang, Xipeng Qiu, Dahua Lin	2024	1
8	Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks Chonghua Wang, E. A. Eeley, Songyang Zhang, Dahua Lin, Kai Chen	2024	0
9	VLMEvalKit: An Open-Source ToolKit for Evaluating Large Multi-Modality Models Haodong Duan, 福岡幸雄, cardog, F Wulff, Lin Chen, حمیدرضا تاج نسائی, Xiaoyi Dong, Yuhang Zang, J.C Kusznir, Keitaro Doi, Dahua Lin, Kai Chen	2024	13
10	Weakly Supervised 3-D Building Reconstruction From Monocular Remote Sensing Images IEEE Transactions on Geoscience and Remote Sensing ·Weijia Li, Y. Cofie, Lingxuan Meng, Jinwang Wang, Juepeng Zheng, Runmin Dong, Conghui He, Gui-Song Xia, Haohuan Fu, Dahua Lin	2024	3
11	Scene as Occupancy The HKU Scholars Hub (University of Hong Kong) ·Wenwen Tong, Chonghao Sima, Tai Wang, Li Chen, Carmen Maria Lopez, Hanming Deng, Yi Gu, Lewei Lu, Ping Luo, Dahua Lin, Hongyang Li	2023	47
12	HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE Almir vieira de., Anyi Rao, Bo Dai, Dahua Lin	2023	0
13	Joint semantic–geometric learning for polygonal building segmentation from high-resolution remote sensing images ISPRS Journal of Photogrammetry and Remote Sensing ·Weijia Li, Wenqian Zhao, Jinhua Yu, Juepeng Zheng, Conghui He, Haohuan Fu, Dahua Lin	2023	36
14	SPTS v2: Single-Point Scene Text Spotting IEEE Transactions on Pattern Analysis and Machine Intelligence ·Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Andrew Jannett, Kyeong-Jun Moon, Can Huang, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin	2023	19
15	FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin Hit paper breakdown →	2021	392
16	FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding The HKU Scholars Hub (University of Hong Kong) ·Dian Shao, Yue Zhao, Bo Dai, Dahua Lin	2020	181
17	Open Compound Domain Adaptation Ziwei Liu, Zhongqi Miao, Xingang Pan, Xiaohang Zhan, Dahua Lin, Stella X. Yu, Boqing Gong	2020	70
18	Optimizing Video Object Detection via a Scale-Time Lattice Kai Chen, Jiaqi Wang, Shuo Yang, Wolfram Höll, Yuanjun Xiong, Chen Change Loy, Dahua Lin	2018	77
19	Contrastive Learning for Image Captioning The HKU Scholars Hub (University of Hong Kong) ·Bo Dai, Dahua Lin	2017	46
20	Coupling Nonparametric Mixtures via Latent Dirichlet Processes Neural Information Processing Systems ·Dahua Lin, John W. Fisher	2012	7

About Dahua Lin

Dahua Lin is a scholar working on Computer Vision and Pattern Recognition, Computer Graphics and Computer-Aided Design, Artificial Intelligence, Computational Mathematics and Signal Processing, having authored 201 papers that have together received 15.8k indexed citations. Recurring topics across this work include Advanced Neural Network Applications (35 papers), Human Pose and Action Recognition (32 papers), Multimodal Machine Learning Applications (32 papers), Advanced Vision and Imaging (31 papers), Advanced Image and Video Retrieval Techniques (31 papers), Domain Adaptation and Few-Shot Learning (23 papers), Video Analysis and Summarization (19 papers) and 3D Shape Modeling and Analysis (19 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (11.8k citations), Artificial Intelligence (6.0k citations), Human-Computer Interaction (1.0k citations), Media Technology (929 citations) and Computer Graphics and Computer-Aided Design (272 citations). Dahua Lin has collaborated with scholars based in Hong Kong, China and United States. Frequent co-authors include Yuanjun Xiong, Sijie Yan, Stella X. Yu, Zhirong Wu, Chen Change Loy, Kai Chen, Jiangmiao Pang, Bo Dai, Jianping Shi and Wanli Ouyang. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, IEEE Transactions on Multimedia, ACM Transactions on Graphics and Neurocomputing.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact