Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning

1 code implementation • CVPR 2022 • Minghang Zheng, Yanjie Huang, Qingchao Chen, Yuxin Peng, Yang Liu

Moreover, they train their model to distinguish positive visual-language pairs from negative ones randomly collected from other videos, ignoring the highly confusing video segments within the same video.

Model Optimization Sentence +1