Weixiong Lin — accepted AI-conference papers

2025

Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training

Haicheng Wang, Chen Ju, Weixiong Lin, Shuai Xiao, Mengting Chen, Yixuan Huang +6

CVPR 2025poster

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text) contrastive paradigm to learn alignment from large-scale messy web d…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2025

Contrast-Unity for Partially-Supervised Temporal Sentence Grounding

Haicheng Wang, Chen Ju, Weixiong Lin, Chaofan Ma, Shuai Xiao, Ya Zhang +1

ICASSP 2025accepted

Temporal sentence grounding aims to detect event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great results but requires expensive annotation costs; while the weakly-supervised setting adopts cheap labels but performs…

Cited by 0 Source ↗Scholar ↗