Expanding Language-Image Pretrained Models for General Video Recognition by Microsoft.
Video-specific prompting scheme, which leverages video content information for generating discriminative textual prompts.
Github: https://github.com/microsoft/VideoX/tree/master/X-CLIP
Paper: https://arxiv.org/abs/2208.02816v1
Dataset: https://paperswithcode.com/dataset/ucf101
👉 @bigdata_1
Post #781
616
- ⚡ 1
- ❤ 1