CLIP4Clip icon indicating copy to clipboard operation
CLIP4Clip copied to clipboard

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

Results 28 CLIP4Clip issues
Sort by recently updated
recently updated
newest added

1.Is there a simple example to run an inference Eg: python infer.py --model --input 'red car', and return the video(s) or url(s) or something like that. 2. Is it possible...

# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...

您好,我注意到您在论文3.2节中的公式(3)提到使用了type embedding来进行多模态融合,但是我在代码中发现type embedding相关的层都被注释掉了。在类似结构迁移到其他多模态任务上时,是否需要使用type embedding呢

Thanks for sharing your wonderful work! When I train on DiDeMo dataset, the following information appears on the terminal more than once. ![139ae0410327e9b89ba27ca5d1d6cfe](https://user-images.githubusercontent.com/57708696/202698891-ffa1c6f4-f15a-4a40-82c6-6c04ddcf0999.png) But the model training was not interrupted....

Hi! Thank you for your great work! I came across your paper where you mentioned that "3D linear generates worse results than 2D linear...., and will pretrain on a large...