no code implementations • 30 Jul 2023 • Wenqing Wang, Kaifeng Gao, Yawei Luo, Tao Jiang, Fei Gao, Jian Shao, Jianwen Sun, Jun Xiao
Video-based scene graph generation (VidSGG) is an approach that aims to represent video content in a dynamic graph by identifying visual entities and their relationships.
1 code implementation • 1 Feb 2023 • Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, Qianru Sun
Without bells and whistles, our RePro achieves a new state-of-the-art performance on two VidVRD benchmarks of not only the base training object and predicate categories, but also the unseen ones.
no code implementations • 25 Apr 2022 • Shaoning Xiao, Long Chen, Kaifeng Gao, Zhao Wang, Yi Yang, Zhimeng Zhang, Jun Xiao
From the view of feature, we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities.
1 code implementation • CVPR 2022 • Kaifeng Gao, Long Chen, Yulei Niu, Jian Shao, Jun Xiao
To this end, we propose a new classification-then-grounding framework for VidSGG, which can avoid all the three overlooked drawbacks.
1 code implementation • 19 Aug 2021 • Kaifeng Gao, Long Chen, Yifeng Huang, Jun Xiao
Video Visual Relation Detection (VidVRD), has received significant attention of our community over recent years.
no code implementations • 23 Mar 2020 • Kaifeng Gao, Gang Mei, Francesco Piccialli, Salvatore Cuomo, Jingzhi Tu, Zenan Huo
It first surveys the popular machine learning algorithms that are developed in the Julia language.