Major1994 comments

Repositories
Issues
Comments

Results 3 comments of


                                            Major1994

S2 pretrained model of InternVideo2 does not work well for Zero-Shot Video-Text Retrieval

> @shepnerd @Wenju-Huang @1093842024 @SHYuanBest I find this bug is because we forget add `model.eval()` in demo, we need to enable it to turn off drop path, now this bug...

NEED HELP: Action Classification low performance

> Can you try the VideoCLIP model? Do you mean InternVideo2_CLIP in InternVideo2/multi_modality/scripts/evaluation/clip/zero_shot/1B/config_k400.py ？ I'm a green hand in this field :PP

NEED HELP: Action Classification low performance

> Can you try the VideoCLIP model? Do you mean abandon internvideo2 and turn to videoclip for action recognition？Your work seems very promising.