๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ป About Me

I am Xuchen Li (ๆŽๆ—ญๅฎธ), an incoming Ph.D. student at Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Kaiqi Huang (IAPR Fellow).

Currently, I am a fourth-year undergraduate student majoring in Computer Science and Technology at School of Computer Science (SCS) at Beijing University of Posts and Telecommunications (BUPT).

I am very grateful to work with Dr. Shiyu Hu, which has a significant impact on me. I am also grateful to grow up and study with my twin brother Xuzhao Li, which is a truly unique and special experience for me.

๐Ÿ”ฅ News

  • 2023.12: ๐Ÿ† Obtain College Scholarship of University of Chinese Academy of Sciences (only 17 students win this scholarship of CASIA)!
  • 2023.12: ๐Ÿ† Obtain China National Scholarship with a rank of 1/455 (0.22%) (the highest honor for undergraduates in China, awarded to top 1% students of BUPT)!
  • 2023.11: ๐Ÿ† Obtain Beijing Merit Student (only 36 students obtain this honor of BUPT)!
  • 2023.09: ๐Ÿ“ One paper has been accepted by the 37th Conference on Neural Information Processing Systems (NeurIPS, CCF-A Conference, Poster)!
  • 2022.12: ๐Ÿ† Obtain Huawei AI Education Base Scholarship (only 20 students win this scholarship of BUPT)!
  • 2022.12: ๐Ÿ† Obtain China National Scholarship with a rank of 2/430 (0.47%) (the highest honor for undergraduates in China, awarded to top 1% students of BUPT)!

๐Ÿ”ฌ Research Interests

Visual Language Tracking (VLT)

  • Research on multi-modal tracking, addressing challenges related to integrating visual and linguistic information for improved tracking accuracy.
  • Research on VLT extends to tasks involving comprehensive video understanding and encompasses efforts to enhance the algorithmsโ€™ capability to interpret and contextualize objects in videos based on linguistic input.
  • The exploration of human-computer interaction patterns employs Large Language Models (LLMs) in conjunction with visual language tracking as a proxy task, contributing to developing more intuitive and user-friendly interactions.

Visual Object Tracking (VOT)

  • Research on visual object tracking algorithms within diverse scenes, aims to enhance the understanding and performance of single object tracking in various scenarios.
  • Research on the robustness and generalization aspects of single object tracking algorithms, investigates the algorithmsโ€™ ability to adapt across diverse scenarios, ensuring consistent and reliable performance.

๐Ÿ“– Educations

sym

2020.09 - now, Undergraduate student
Computer Science and Technology, Ranking 4/442 (0.9%)
School of Computer Science
Beijing University of Posts and Telecommunications, Beijing

๐Ÿ’ป Research Experiences

๐Ÿ“ Publications

Acceptance

NeurIPS 2023
sym

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship

Shiyu Hu, Dailing Zhang, Meiqi Wu, Xiaokun Feng, Xuchen Li, Xin Zhao, Kaiqi Huang

NeurIPS 2023 (CCF-A Conference, Poster): the 37th Conference on Neural Information Processing Systems
[PDF] [Poster] [Slides] [Platform] [Toolkit]

Under Review

IJCAI 2024
sym

Remembering Target More Like Humans: A Robust Visual-Language Tracker with Adaptive Prompts

Xiaokun Feng, Xuchen Li, Shiyu Hu, Dailing Zhang, Meiqi Wu, Xiaotang Chen, Kaiqi Huang

IJCAI 2024 (CCF-A Conference, Under Review): the 33rd International Joint Conference on Artificial Intelligence

๐ŸŽ– Honors and Awards

  • China National Scholarship, My Rank: 1/455 (0.22%), at BUPT, by Ministry of Education of China, 2023
  • China National Scholarship, My Rank: 2/430 (0.47%), at BUPT, by Ministry of Education of China, 2022
  • China National Encouragement Scholarship, My Rank: 8/522 (1.53%), at BUPT, by Ministry of Education of China, 2021
  • Huawei AI Education Base Scholarship, at BUPT, by Ministry of Education of China and Huawei AI Education Base Joint Working Group, 2022
  • College Scholarship of University of Chinese Academy of Sciences, at CASIA, by University of Chinese Academy of Sciences, 2023
  • Haohan Scholarship and Grants, at BUPT, by Beijing Haohan DATA Technology Co., Ltd, 2021
  • Beijing Merit Student, at BUPT, by Beijing Municipal Education Commission, 2023
  • National First Prize, China Collegiate Computing Contest-Artificial Intelligence Innovation Contest (team leader), 2022
  • Meritorious Winner, Mathematical Contest in Modeling and Interdisciplinary Contest in Modeling, 2022
  • National Third Prize, Huawei Information and Communication Technology Competition Nationwide Final (team leader), 2023
  • National Third Prize, China Robotics and Artificial Intelligence Competition, 2023
  • National Level Project, College Studentsโ€™ Innovation and Entrepreneurship Training Program (team leader), 2023
  • National Level Project, College Studentsโ€™ Innovation and Entrepreneurship Training Program, 2023

๐ŸŒŸ Maintained Projects

VideoCube / MGIT Platform
sym

VideoCube: A Large-scale Multi-dimensional Global Instance Tracking Intelligent Evaluation Platform
MGIT: A Multi-modal Global Instance Tracking Benchmark Based on Hierarchical Semantic Framework

  • Visual Object Tracking / Visual Language Tracking / Long Video Understanding and Reasoning / Intelligent Evaluation Technology
  • As of Feb. 2024, the platform has received 315k+ page views, 1k+ downloads, 400+ trackers from 130+ countries and regions worldwide.
  • VideoCube / MGIT is the supporting platform for research accepted by IEEE TPAMI 2022 and NeurIPS 2023.
SOTVerse Platform
sym

SOTVerse: A User-defined Single Object Tracking Task Space

  • Visual Object Tracking / Dynamic Open Environment Construction / Visual Evaluation Technique
  • As of Feb. 2024, the platform has received 106k+ page views from 100+ countries and regions worldwide.
  • SOTVerse is the supporting platform for research accepted by IJCV 2023.
GOT-10k Platform
sym

GOT-10k: A Large High-diversity Benchmark and Evaluation Platform for Single Object Tracking

  • Visual Object Tracking / Evaluation Technology / Platform Maintenance
  • As of Feb. 2024, the platform has received 3.24M+ page views, 6k+ downloads, 18k+ trackers from 160+ countries and regions worldwide.
  • GOT-10k is the supporting platform for research accepted by IEEE TPAMI 2019.

๐Ÿ”— For More Info

๐Ÿค Collaborators

My homepage visitors recorded from February, 2024. Thanks for attention.