[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
-
Updated
May 23, 2024 - Python
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.
Video Foundation Models & Data for Multimodal Understanding
Official code for MiniGPT4-video
[ACL 2020] PyTorch code for TVQA+: Spatio-Temporal Grounding for Video Question Answering
[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video (ICML 2023)
[ICCV 2021 Oral + TPAMI] Just Ask: Learning to Answer Questions from Millions of Narrated Videos
Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Pre-training Dataset and Benchmarks
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)
Video Graph Transformer for Video Question Answering (ECCV'22)
A PyTorch implementation of VIOLET
Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)
[NeurIPS 2022 Spotlight] Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models (CVPR 2023)
ROCK model for Knowledge-Based VQA in Videos
PyTorch code for ROLL, a knowledge-based video story question answering model.
A simple attention deep learning model to answer questions about a given video with the most relevant video intervals as answers.
[CVPR 2023 Highlight] Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Add a description, image, and links to the video-question-answering topic page so that developers can more easily learn about it.
To associate your repository with the video-question-answering topic, visit your repo's landing page and select "manage topics."