Hengduo Li

804 total citations
12 papers, 315 citations indexed

About

Hengduo Li is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Human-Computer Interaction. According to data from OpenAlex, Hengduo Li has authored 12 papers receiving a total of 315 indexed citations (citations by other indexed papers that have themselves been cited), including 10 papers in Computer Vision and Pattern Recognition, 3 papers in Artificial Intelligence and 1 paper in Human-Computer Interaction. Recurrent topics in Hengduo Li's work include Human Pose and Action Recognition (6 papers), Multimodal Machine Learning Applications (5 papers) and Advanced Neural Network Applications (5 papers). Hengduo Li is often cited by papers focused on Human Pose and Action Recognition (6 papers), Multimodal Machine Learning Applications (5 papers) and Advanced Neural Network Applications (5 papers). Hengduo Li collaborates with scholars based in United States, China and Singapore. Hengduo Li's co-authors include Larry S. Davis, Zuxuan Wu, Caiming Xiong, Abhinav Shrivastava, Yu–Gang Jiang, Chen Zhu, Richard Socher, Guyue Zhang, Jun Liu and Yan Qiu Chen and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision and IEEE Transactions on Multimedia.

In The Last Decade

Hengduo Li

11 papers receiving 307 citations

Peers

Countries citing papers authored by Hengduo Li

Since Specialization

Citations

This map shows the geographic impact of Hengduo Li'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 Hengduo Li with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Hengduo Li more than expected).

Fields of papers citing papers by Hengduo Li

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Hengduo Li. 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 Hengduo Li. The network helps show where Hengduo Li may publish in the future.

Co-authorship network of co-authors of Hengduo Li

This figure shows the co-authorship network connecting the top 25 collaborators of Hengduo Li. A scholar is included among the top collaborators of Hengduo Li based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Hengduo Li. Hengduo Li is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

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

12 of 12 papers shown

#	Work	Indexed citations
1	BMB: Balanced Memory Bank for Long-Tailed Semi-Supervised Learning 2025 ·IEEE Transactions on Multimedia ·(unknown), (unknown), Hengduo Li, Zuxuan Wu, Yu–Gang Jiang	0
2	MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding 2024 ·Bo He, Hengduo Li, (unknown), Menglin Jia, Xuefei Cao, Ashish H. Shah, (unknown), Ser-Nam Lim	19
3	Object Recognition as Next Token Prediction 2024 ·(unknown), (unknown), Jonas Geiping, Hengduo Li, Tom Goldstein, Ser-Nam Lim	1
4	HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition 2022 ·ACM Transactions on Multimedia Computing Communications and Applications ·(unknown), Zuxuan Wu, Hengduo Li, Jingjing Chen, Yu–Gang Jiang	4
5	Rethinking Pseudo Labels for Semi-supervised Object Detection 2022 ·Proceedings of the AAAI Conference on Artificial Intelligence ·Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis	58
6	A Coarse-to-Fine Framework for Resource Efficient Video Recognition 2021 ·International Journal of Computer Vision ·Zuxuan Wu, Hengduo Li, Yingbin Zheng, Caiming Xiong, Yu–Gang Jiang, Larry S. Davis	29
7	2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition 2021 ·Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis	19
8	Learning From Noisy Anchors for One-Stage Object Detection 2020 ·Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S. Davis	78
9	A Dynamic Frame Selection Framework for Fast Video Recognition 2020 ·IEEE Transactions on Pattern Analysis and Machine Intelligence ·Zuxuan Wu, Hengduo Li, Caiming Xiong, Yu–Gang Jiang, Larry S. Davis	40
10	Transferable Clean-Label Poisoning Attacks on Deep Neural Nets 2019 ·Repository for Publications and Research Data (ETH Zurich) ·Chen Zhu, (unknown), Hengduo Li, Gavin Taylor, Christoph Studer, Tom Goldstein	8
11	Multi-glimpse LSTM with color-depth feature fusion for human detection 2017 ·Hengduo Li, Jun Liu, Guyue Zhang, Yuan Gao, Yirui Wu	13
12	Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos 2017 ·IEEE Signal Processing Letters ·Guyue Zhang, Jun Liu, Hengduo Li, Yan Qiu Chen, Larry S. Davis	46

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