幸运的小菜鸟的博客

“Video summarization” refers to the process of creating a concise and condensed representation of a video, capturing its essential content, key events, or highlights. The goal is to provide a shorter version of the video that retains its most important inf

YearNameAreamodeldescriptiondrawback2021 ICMLClip （Contrastive Language-Image Pre-training）contrastive learning、zero-shot learing、mutimodel用文本作为监督信号来训练可迁移的视觉模型CLIP’s zero-shot performance, although comparable to supervised ResNet50, is n