https://github.com/OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
https://github.com/OpenGVLab/InternVideo

action-recognition benchmark contrastive-learning foundation-models instruction-tuning masked-autoencoder multimodal open-set-recognition self-supervised spatio-temporal-action-localization temporal-action-localization video-clip video-data video-dataset video-question-answering video-retrieval video-understanding vision-transformer zero-shot-classification zero-shot-retrieval

Last synced: 7 days ago
JSON representation

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

• Host: GitHub
• URL: https://github.com/OpenGVLab/InternVideo
• Owner: OpenGVLab
• License: apache-2.0
• Created: 2022-11-23T12:57:00.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-08-27T12:08:53.000Z (2 months ago)
• Last Synced: 2024-09-06T11:04:55.576Z (about 2 months ago)
• Topics: action-recognition, benchmark, contrastive-learning, foundation-models, instruction-tuning, masked-autoencoder, multimodal, open-set-recognition, self-supervised, spatio-temporal-action-localization, temporal-action-localization, video-clip, video-data, video-dataset, video-question-answering, video-retrieval, video-understanding, vision-transformer, zero-shot-classification, zero-shot-retrieval
• Language: Python
• Homepage:
• Size: 53.2 MB
• Stars: 1,288
• Watchers: 28
• Forks: 83
• Open Issues: 83
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project