InternVideo
InternVideo copied to clipboard
OpenGVLab
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
Hi, When can we expect the demo for model usage to be released? Best regards, Archana
Hello! I have been able to successfully use the features posted in [Temporal Action Localization](https://github.com/OpenGVLab/InternVideo/tree/main/Downstream/Temporal-Action-Localization) to reproduce great results on their respective datasets. Are you planning to release the weights...
Hi, I was wondering if the code for evaluating on AVA-Kinetics is available somewhere in the current codebase. In the file 'https://github.com/OpenGVLab/InternVideo/blob/main/Downstream/Spatial-Temporal-Action-Localization/run_class_finetuning.py' L239-242, it seems that only evaluation on AVA...
Hello, thanks for your good work! I encountered some problems when reproducing the performance of Temporal-Action-Localization task: Thumos14: 69.11 average mAP (lower than 71.58). The input_dim of feature is not...
May I ask which code you use to extract frames of FineAction? I use https://github.com/open-mmlab/mmaction2/blob/main/tools/data/build_rawframes.py to extract frames, but some videos cannot be extracted.
Thanks for the great work! The model zoo has already released many pretrained model weights and task ones, but there is still a lack of checkpoint for the AVA dataset....
Hello I'm trying to use your project for some project them I'm working on, I've trouble to setup the environment with conda if you have a yaml file that I...
ssv2. full_tuning --test_num_segment 2 \ --test_num_crop 3 \ to --test_num_segment 4 \ --test_num_crop 3 \ ``` InternVideo/InternVideo2/single_modality/models/internvideo2.py", line 527, in forward x = x + pos_embed RuntimeError: The size of...
