Video Understanding Python Packages

lmms-eval

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

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

telemem

TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

gurrt

An Intelligent Open Source Video Understanding System A different path from traditional Large Video Language Models (LVLMs). Built for modularity, openness, and real world usability.

vidchain

VidChain: High-fidelity multimodal RAG framework featuring the IRIS Intelligence Agent

vid2llm

Turn any video into LLM-ready frames. Smart sampling, scene detection, OCR, and SDK-ready output for modern multimodal language models.

ppvideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

video2tfrecord

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.

videobench

Human Preference Aligned Video Generation Benchmark

vss-ctx-rag

No description available

mmaction

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

habench

Human Preference Aligned Video Generation Benchmark

paddlevideo

Awesome Video toolkits based on PaddlePaddle

live-bench

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

otxmmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark