Qinxun Bai

1.9k total citations · 1 hit paper
8 papers, 1.1k citations indexed

About

Qinxun Bai is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Computational Theory and Mathematics. According to data from OpenAlex, Qinxun Bai has authored 8 papers receiving a total of 1.1k indexed citations (citations by other indexed papers that have themselves been cited), including 5 papers in Computer Vision and Pattern Recognition, 3 papers in Artificial Intelligence and 2 papers in Computational Theory and Mathematics. Recurrent topics in Qinxun Bai's work include Video Surveillance and Tracking Methods (3 papers), Multimodal Machine Learning Applications (2 papers) and Human Pose and Action Recognition (2 papers). Qinxun Bai is often cited by papers focused on Video Surveillance and Tracking Methods (3 papers), Multimodal Machine Learning Applications (2 papers) and Human Pose and Action Recognition (2 papers). Qinxun Bai collaborates with scholars based in United States, China and Canada. Qinxun Bai's co-authors include Xingchao Peng, Kate Saenko, Bo Wang, Xide Xia, Zijun Huang, Stan Sclaroff, Qi Feng, Vitaly Ablavsky, Margrit Betke and Zheng Wu and has published in prestigious journals such as OpenBU/Boston University Institutional Repository (Boston University), arXiv (Cornell University) and International Conference on Machine Learning.

In The Last Decade

Qinxun Bai

8 papers receiving 1.1k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Moment Matching for Multi-Source Domain Adaptation

2019 918 citations Xingchao Peng, Qinxun Bai et al. profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Qinxun Bai United States	6	811	710	87	79	41	8	1.1k
Xide Xia United States	5	866 1.1×	678 1.0×	88 1.0×	79 1.0×	38 0.9×	5	1.1k
Xingchao Peng United States	7	980 1.2×	845 1.2×	100 1.1×	105 1.3×	47 1.1×	9	1.3k
Mahsa Baktashmotlagh Australia	15	580 0.7×	482 0.7×	68 0.8×	46 0.6×	43 1.0×	39	945
Mengmeng Jing China	15	619 0.8×	420 0.6×	86 1.0×	77 1.0×	37 0.9×	29	797
Han Zhao United States	13	729 0.9×	404 0.6×	44 0.5×	67 0.8×	54 1.3×	46	961
Sachin Ravi United States	5	1.0k 1.3×	706 1.0×	68 0.8×	147 1.9×	25 0.6×	5	1.2k
Yogesh Balaji United States	10	772 1.0×	879 1.2×	76 0.9×	169 2.1×	37 0.9×	13	1.2k
Junbao Zhuo China	7	499 0.6×	405 0.6×	50 0.6×	65 0.8×	29 0.7×	19	656
Yaoyao Liu Germany	5	683 0.8×	474 0.7×	43 0.5×	123 1.6×	27 0.7×	6	923
David Dohan United States	5	548 0.7×	700 1.0×	51 0.6×	132 1.7×	58 1.4×	10	1.0k

Countries citing papers authored by Qinxun Bai

Since Specialization

Citations

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

Fields of papers citing papers by Qinxun Bai

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Qinxun Bai

This figure shows the co-authorship network connecting the top 25 collaborators of Qinxun Bai. A scholar is included among the top collaborators of Qinxun Bai 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 Qinxun Bai. Qinxun Bai 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:

8 of 8 papers shown

1.

Zhou, Zhengyuan, et al.. (2021). Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning. International Conference on Artificial Intelligence and Statistics. 3331–3339. 7 indexed citations

2.

Feng, Qi, Vitaly Ablavsky, Qinxun Bai, & Stan Sclaroff. (2021). Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers. 5847–5856. 58 indexed citations

3.

Feng, Qi, Vitaly Ablavsky, Qinxun Bai, Guorong Li, & Stan Sclaroff. (2020). Real-time Visual Object Tracking with Natural Language Description. 689–698. 48 indexed citations

4.

Peng, Xingchao, Qinxun Bai, Xide Xia, et al.. (2019). Moment Matching for Multi-Source Domain Adaptation. 1406–1415. 918 indexed citations breakdown →

5.

Chen, Chao, et al.. (2018). A Topological Regularizer for Classifiers via Persistent Homology. arXiv (Cornell University). 2573–2582. 14 indexed citations

6.

Bai, Qinxun, Steven Rosenberg, Zheng Wu, & Stan Sclaroff. (2016). Differential geometric regularization for supervised learning of classifiers. OpenBU/Boston University Institutional Repository (Boston University). 1879–1888. 1 indexed citations

7.

Bai, Qinxun, Henry Lam, & Stan Sclaroff. (2014). A Bayesian Framework for Online Classifier Ensemble. International Conference on Machine Learning. 1584–1592. 4 indexed citations

8.

Bai, Qinxun, et al.. (2013). Randomized Ensemble Tracking. 2040–2047. 74 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