Beyond RNNs: Positional self-attention with co-attention for video question answeringXiangpeng LiJingkuan Songet al.2019AAAI 2019
HCMA '23: 4th International Workshop on Human-Centric Multimedia AnalysisJingkuan SongWu Liuet al.2023MM 2023
HCMA 22: 3rd InternationalWorkshop on Human-centric Multimedia AnalysisDingwen ZhangChaowei Fanget al.2022MM 2022
HUMA'21: 2nd International Workshop on Human-centric Multimedia AnalysisWu LiuXinchen Liuet al.2021MM 2021
Text-instance graph: Exploring the relational semantics for text-based visual question answeringXiangpeng LiBo Wuet al.2022Pattern Recognition