- Name: Yunchuan Ma
- University: University of Chinese Academy of Sciences
- Department: School of Computer Science and Technology
- Program: Ph.D. Candidate, Second Year
- Research Fields: Video Understanding, Vision and Language
- Google Scholar: My Google Scholar Profile
Publications
- Style-aware two-stage learning framework for video captioning
Y Ma, Z Zhu, Y Qi, A Beheshti, Y Li, L Qing, G Li
Knowledge-Based Systems 301, 112258
- Towards Subject-Oriented Video Captioning via User-Specified Targets
Y Ma, C Teng, Y Qi, G Li, L Qing, Q Wu, Q Huang
Under Review
- RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning
Y Ma, L Qing, G Li, Y Qi, QZ Sheng, Q Huang
Pattern Recognition
- TRA: Text Refinement and Alignment Framework for Point-supervised Temporal Action Localization
Y Ma, L Qing, G Li, Y Liu, Y Qi, Q Huang
Under Review
- Boosting UAV Detection via Memory-Enhanced Attention and Contrastive Learning
Y Liu*, Y Ma*, Y Qi, G Li, L Qing
IEEE Signal Processing Letters
- Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localizationg
Y Ma, L Qing, G Li, Y Liu, Y Qi, Q Huang
Under Review