[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Papers, code and datasets about deep learning and multi-modal learning for video analysis

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving & Foundation Models in Autonomous System

Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.

Awesome papers & datasets specifically focused on long-term videos.

500,000 multimodal short video data and baseline models. 50万条多模态短视频数据集和基线模型（TensorFlow2.0）。

Summary about Video-to-Text datasets. This repository is part of the review paper *Bridging Vision and Language from the Video-to-Text Perspective: A Comprehensive Review*

SoccerAct10 is a dataset which contains 10 different soccer actions. This dataset was developed using the videos from YouTube.

Surveillance Perspective Human Action Recognition Dataset: 7759 Videos from 14 Action Classes, aggregated from multiple sources, all cropped spatio-temporally and filmed from a surveillance-camera like position.

Tools for loading video dataset and transforms on video in pytorch. You can directly load video files without preprocessing.

🌱 Starter kit for working with the EPIC-KITCHENS-55 dataset for action recognition or anticipation

Official Code for VideoLT: Large-scale Long-tailed Video Recognition (ICCV 2021)

Official repository for the paper titled "Bitstream-corrupted Video Recovery: A Novel Benchmark Dataset and Method", accepted by NeurIPS 2023 Dataset and Benchmark Track

Keras 3 Implementation of Video Swin Transformers for 3D Video Modeling

Official repo of the paper "MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos"

[AAAI 2023] AVCAffe: A Large Scale Audio-Visual Dataset of Cognitive Load and Affect for Remote Work

Official This-Is-My Dataset published in CVPR 2023

[NeurIPS'22] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification

Synthetically Generated Surveillance Perspective Human Action Recognition Dataset: 6901 Videos from 10 action classes, made by a 3D Simulation, all cropped spatio-temporally and filmed from a surveillance-camera like position.