#Video-understanding
Showing 21 of 21 repositories tagged #video-understanding, ranked by stars
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.
awesome grounding: A curated list of research papers in visual grounding
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
A collection of recent video understanding datasets, under construction!
Tools for movie and video research
deep learning sex position classifier
Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction". And for the ECCV'20 SimAug paper.
Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.
[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.
Video Generation Benchmark
Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs
FreeVA: Offline MLLM as Training-Free Video Assistant
The official code of "CSTA: CNN-based Spatiotemporal Attention for Video Summarization"
[NeurIPS 2025] Deep Memory Backtracking for Long Video Understanding
Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Official PyTorch implementation of "Video Summarization with Large Language Models" (CVPR 2025).