Thang Vu

847 total citations · 1 hit paper
12 papers, 303 citations indexed

About

Thang Vu is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Computational Mechanics. According to data from OpenAlex, Thang Vu has authored 12 papers receiving a total of 303 indexed citations (citations by other indexed papers that have themselves been cited), including 9 papers in Artificial Intelligence, 7 papers in Computer Vision and Pattern Recognition and 3 papers in Computational Mechanics. Recurrent topics in Thang Vu's work include Domain Adaptation and Few-Shot Learning (5 papers), Advanced Neural Network Applications (4 papers) and Reinforcement Learning in Robotics (3 papers). Thang Vu is often cited by papers focused on Domain Adaptation and Few-Shot Learning (5 papers), Advanced Neural Network Applications (4 papers) and Reinforcement Learning in Robotics (3 papers). Thang Vu collaborates with scholars based in South Korea, Israel and Germany. Thang Vu's co-authors include Chang D. Yoo, Tung M. Luu, Thanh Minh Nguyen, Trung X. Pham, Junyeong Kim, Ofer Hadar, Chaoning Zhang, Ilia Polian and Xuan Nguyen and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Access and Sensors.

In The Last Decade

Thang Vu

12 papers receiving 296 citations

Hit Papers

SoftGroup for 3D Instance Segmentation on Point Clouds 2022 2026 2023 2024 2022 50 100 150

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Thang Vu South Korea 7 177 86 73 63 57 12 303
Shiyi Lan United States 5 208 1.2× 100 1.2× 78 1.1× 55 0.9× 52 0.9× 6 310
Liuyuan Deng China 8 254 1.4× 58 0.7× 64 0.9× 76 1.2× 64 1.1× 15 391
Qiguang Miao China 10 153 0.9× 86 1.0× 80 1.1× 67 1.1× 48 0.8× 45 294
Jiantao Gao China 8 224 1.3× 115 1.3× 69 0.9× 60 1.0× 35 0.6× 16 329
Jianhui Liu China 6 300 1.7× 71 0.8× 72 1.0× 84 1.3× 38 0.7× 18 424
Siqi Fan China 6 107 0.6× 134 1.6× 133 1.8× 138 2.2× 26 0.5× 24 320
Shuaifeng Zhi China 9 329 1.9× 129 1.5× 99 1.4× 50 0.8× 70 1.2× 26 487
Tung M. Luu South Korea 6 100 0.6× 85 1.0× 70 1.0× 55 0.9× 31 0.5× 11 206
Armin Mustafa United Kingdom 6 219 1.2× 40 0.5× 24 0.3× 26 0.4× 34 0.6× 19 277
Songfang Han United States 8 308 1.7× 114 1.3× 117 1.6× 70 1.1× 27 0.5× 12 412

Countries citing papers authored by Thang Vu

Since Specialization
Citations

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

Fields of papers citing papers by Thang Vu

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Thang Vu

This figure shows the co-authorship network connecting the top 25 collaborators of Thang Vu. A scholar is included among the top collaborators of Thang Vu 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 Thang Vu. Thang Vu is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

12 of 12 papers shown
1.
Vu, Thang, et al.. (2023). Scalable SoftGroup for 3D Instance Segmentation on Point Clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence. 46(4). 1981–1995. 11 indexed citations
2.
Pham, Trung X., et al.. (2023). DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning. IEEE Access. 11. 21534–21545. 6 indexed citations
3.
Vu, Thang, et al.. (2022). SoftGroup for 3D Instance Segmentation on Point Clouds. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2698–2707. 155 indexed citations breakdown →
4.
Hadar, Ofer, et al.. (2022). Human vs. Automatic Detection of Deepfake Videos Over Noisy Channels. 2022 IEEE International Conference on Multimedia and Expo (ICME). 1–6. 2 indexed citations
5.
Luu, Tung M., et al.. (2022). Utilizing Skipped Frames in Action Repeats for Improving Sample Efficiency in Reinforcement Learning. IEEE Access. 10. 64965–64975. 1 indexed citations
6.
Luu, Tung M., et al.. (2022). Visual Pretraining via Contrastive Predictive Model for Pixel-Based Reinforcement Learning. Sensors. 22(17). 6504–6504. 3 indexed citations
7.
Luu, Tung M., et al.. (2021). Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model. 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 3471–3477. 12 indexed citations
8.
Vu, Thang, et al.. (2021). Learning Imbalanced Datasets With Maximum Margin Loss. arXiv (Cornell University). 1269–1273. 10 indexed citations
9.
10.
Vu, Thang, et al.. (2021). SCNet: Training Inference Sample Consistency for Instance Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 35(3). 2701–2709. 66 indexed citations
11.
Vu, Thang, et al.. (2020). SCNet: Training Inference Sample Consistency for Instance Segmentation. arXiv (Cornell University). 35(3). 2701–2709. 3 indexed citations
12.
Vu, Thang, et al.. (2019). Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution. arXiv (Cornell University). 32. 1430–1440. 33 indexed citations

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

Rankless by CCL
2026