Contact MVA2025

đź‘‘Winners of the Small Multi-Object Tracking for Spotting Birds (SMOT4SB) Challenge 2025

MVA2025 Winners

The Small Multi-Object Tracking for Spotting Birds Challenge 2025 had 78 participants and 308 submissions to CodaBench. The following are the winners who performed remarkably among them.
Congratulations! 🎉

MVA2025 SMOT4SB Challenge Results
Table: Final rankings and performance metrics for the MVA2025 Small Multi-Object Tracking for Spotting Birds Challenge. Results are cited from arXiv:2507.12832.

👑1st Place

DL Team
"YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association"
arXiv
Xiang Yu1, Guang Liang1, Xinyao Liu2
1Nanjing University, China
2University of Science and Technology of China, China


👑2nd Place

zhwa2003
"Intersection-based Ensemble for Small Multi-Object Tracking in Challenging Environments"
Peer-reviewed paper
IEEE Xplore arXiv
Guan-Zhang Wang1, Wei-Ta Chu1
1National Cheng Kung University, Taiwan


👑3rd Place

elsalabA
"Boosting Small Object Tracking via Collaborative Detection Transformer"
Peer-reviewed paper
IEEE Xplore arXiv
Bing-Cheng Chuang1, Jia-Hua Lee1, Pin-Tseng Kuo1, I-Hsuan Chu1, Yi-Shein Hsiao1, Cheng-Han Wu1, Po-Yi Wu2, Jui-Chien Tsou2, Hsuan-Chi Liu2, Chun-Yi Lee2, Yuan-Fu Yang3
1National Tsing Hua University, Taiwan
2National Taiwan University, Taiwan
3National Yang Ming Chiao Tung University, Taiwan


👑4th Place

sgm11
"Confidence-based Adaptive Weighted Boxes Fusion for Multi-Object Tracking of Small Birds"
Peer-reviewed paper
IEEE Xplore arXiv
Kosuke Shigematsu1, Asuka Shin1
1National Institute of Technology, Oita College, Japan


👑5th Place

xmba15
"Multi-Object Bird Tracking via CenterNet Ensemble and Motion-Compensated OC-SORT"
Ba Tran1
1Axelspace Corporation, Japan