no code implementations • 28 Nov 2023 • Jiaming Zhou, Hanjun Li, Kun-Yu Lin, Junwei Liang
Under the weak supervision setting, action labels are provided for the whole video without precise start and end times of the action clip.
Ranked #1 on Long-video Activity Recognition on Breakfast
no code implementations • 27 Aug 2023 • Xiujun Shu, Wei Wen, Liangsheng Xu, Mingbao Lin, Ruizhi Qiao, Taian Guo, Hanjun Li, Bei Gan, Xiao Wang, Xing Sun
In this paper, we present a unified and dynamic graph (UniDG) framework for temporal character grouping.
1 code implementation • ICCV 2023 • Hanjun Li, Xiujun Shu, Sunan He, Ruizhi Qiao, Wei Wen, Taian Guo, Bei Gan, Xing Sun
Under this setup, we propose a Dynamic Gaussian prior based Grounding framework with Glance annotation (D3G), which consists of a Semantic Alignment Group Contrastive Learning module (SA-GCL) and a Dynamic Gaussian prior Adjustment module (DGA).
Ranked #10 on Temporal Sentence Grounding on Charades-STA
1 code implementation • CVPR 2023 • Bei Gan, Xiujun Shu, Ruizhi Qiao, Haoqian Wu, Keyu Chen, Hanjun Li, Bo Ren
Based on existing efforts, this work has two observations: (1) For different annotators, labeling highlight has uncertainty, which leads to inaccurate and time-consuming annotations.
1 code implementation • CVPR 2022 • Hanjun Li, Xingjia Pan, Ke Yan, Fan Tang, Wei-Shi Zheng
Object detection under imperfect data receives great attention recently.
1 code implementation • CVPR 2021 • Hanjun Li, Gaojie Wu, Wei-Shi Zheng
We propose a novel search space called Combined Depth Space (CDS), based on which we search for an efficient network architecture, which we call CDNet, via a differentiable architecture search algorithm.