no code implementations • 8 Jan 2024 • Long Deng, Ziqiang Li, Bingxin Zhou, Zhongming Chen, Ao Li, Yongxin Ge
Although few-shot action recognition based on metric learning paradigm has achieved significant success, it fails to address the following issues: (1) inadequate action relation modeling and underutilization of multi-modal information; (2) challenges in handling video matching problems with different lengths and speeds, and video matching problems with misalignment of video sub-actions.
no code implementations • 9 Mar 2023 • Caiyuan Chu, Ya Li, Yifan Liu, Jia-Chen Gu, Quan Liu, Yongxin Ge, Guoping Hu
The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels.
no code implementations • 14 Jul 2022 • Ziqiang Li, Yongxin Ge, Jiaruo Yu, Zhongming Chen
With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed videos.
Classification Weakly-supervised Temporal Action Localization +1
no code implementations • 19 Nov 2021 • Huijun Liu, Chunhua Yang, Ao Li, Sheng Huang, Xin Feng, Zhimin Ruan, Yongxin Ge
In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available.
no code implementations • 6 Nov 2013 • Sheng Huang, Dan Yang, Fei Yang, Yongxin Ge, Xiaohong Zhang, Jiwen Lu
We present an improved Locality Preserving Projections (LPP) method, named Gloablity-Locality Preserving Projections (GLPP), to preserve both the global and local geometric structures of data.