NEED HELP: Action Classification low performance
Problems: Use demo to test action classification on kinetics-700 validation set but get very poor result
Experiment:
- Pretrained model: https://huggingface.co/OpenGVLab/InternVideo2-Stage2_1B-224p-f4/tree/main
- text candidate:use the class name of k700 dataset annotation
- dataset:kinetics-700 validation set.
- code:demo.ipynb
example: input:carving ice/nTnAoTQ41Nc_000011_000021.mp4 output: text: coloring in ~ prob: 0.0085 text: acting in play ~ prob: 0.0053 text: smashing ~ prob: 0.0043 text: cracking knuckles ~ prob: 0.0041 text: tasting food ~ prob: 0.0040
Can you try the VideoCLIP model?
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
Can you try the VideoCLIP model?
Do you mean abandon internvideo2 and turn to videoclip for action recognition?Your work seems very promising.
Yes. I'm not sure whether there is a bug in the demo. But I have tested the VideoCLIP on Kinetics and it runs normally.