1. Image-to-word transformation based on dividing and vector quantizing images with words;mori;Proc of the ACM Int Conf on Multimedia,0
2. Adversarial Background-Aware Loss for Weakly-Supervised Temporal Activity Localization
3. Zero-Shot Temporal Action Detection via Vision-Language Prompting
4. Temporal action detection with global segmentation mask learning;nag;Proc of Eur Conf Comput Vis,0
5. Weakly-supervised action localization with expectation-maximization multiinstance learning;luo;Proc of Eur Conf Comput Vis,0