Pinned Loading

1. Flash-VStream Flash-VStream Public

   Forked from IVGSZ/Flash-VStream

   This is the official implementation of "Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams"

   Python 1

2. Memory-Augmented-VLM Memory-Augmented-VLM Public

   Forked from LLaVA-VL/LLaVA-NeXT

   Memory-Augmented Video-Language Model built on top of the LLaVA-OneVision backbone

   Python 1

3. VideoLLaMB VideoLLaMB Public

   Forked from bigai-nlco/VideoLLaMB

   Official Repository of VideoLLaMB: Long Video Understanding with Recurrent Memory Bridges

   Python

4. LLaVA-VL/LLaVA-NeXT LLaVA-VL/LLaVA-NeXT Public

   Python 4.5k 441

5. EvolvingLMMs-Lab/lmms-eval EvolvingLMMs-Lab/lmms-eval Public

   One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

   Python 3.6k 511

6. ncTimTang/AKS ncTimTang/AKS Public

   [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding

   Python 172 13