[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

[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.

Any-length Video Inpainting and Editing with Plug-and-Play Context Control

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.

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

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

Official repo of the ICLR 2025 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

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

The repository contains the code for extracting image and mask from a video segmentation dataset by using the OpenCV library in the Python programming language.

Epic-kitchen video player

This annotation tool is build to clean and create video dataset.

This repository contains the implementation of Enhanced Random Binary Multilevel Attention Network (ERBMA-Net), a novel framework for facial depression recognition. ERBMA-Net addresses key limitations in existing methods by introducing random binary convolutional filters for enhanced adaptability and multilevel attention mechanisms.

the frame extractor for Video Datasets with GPU Acceleration