video-classification

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

Easiest way of fine-tuning HuggingFace video classification models

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022

Multi-modal AI-generated content detection: image, video, and audio. Benchmarks, training code (DINOv2, DINOv3, ReStraV, BreathNet), and evaluation pipeline for real vs. synthetic classification with calibration-aware metrics.

The notebook explains the various steps to obtain the results of publication: "Is Space-Time Attention All You Need for Video Understanding?"

Python script to fine tune Open source Video Vision Transformer (ViVit) using HuggingFace Trainer Library