💬 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: github.com/microso…r/X-CLIP Paper: https://arxiv.org/abs/2208.02816v1 Dataset: https://paperswithcode.com/dataset/ucf101 @ai_machinelearning_big_data