MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding
[ PDF ]
Hongjie Zhang*,
Yi Liu*, Lu Dong*, Yifei Huang, et al.
(under review)
F2S-Net: Learning Frame-To-Segment Prediction for Online Action Detection
Yi Liu, Yu Qiao and Yali Wang.
Journal of Real-Time Image Processing (JRTIP 2024)
Dual Masked Modeling for Weakly-Supervised Temporal Boundary Discovery
[ PDF ]
Yuer Ma*,
Yi Liu*, Wenxiong Kang, Limin Wang, Yu Qiao and Yali Wang.
IEEE Transactions on Multimedia (T-MM 2023)
Learning Discriminative Feature Representation for Open Set Action Recognition
[ PDF ]
Hongjie Zhang*,
Yi Liu*, Limin Wang, Yali Wang and Yu Qiao.
ACM Multimedia (ACM MM 2023)
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
[ Project ] [ PDF ] [ Code ]
Yi Liu*, Limin Wang*, Yali Wang*, Xiao Ma, and Yu Qiao.
IEEE Transactions on Image Processing (T-IP 2022)
VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection
[ Project ] [ PDF ] [ Code ]
Yi Liu*, Xuan Zhang*, Ying Li, Guixin Liang, et al.
International Conference on Pattern Recognition (ICPR 2022)
短视频场景在线起始检测任务及方法研究
[ PDF ]
李煜堃*,
刘熠*, 周林, 何艾莲, 王亚立, 彭小江, 乔宇.
集成技术 (集成技术 2021)