Video Foundation Models & Data for Multimodal Understanding
-
Updated
Jun 4, 2024 - Python
Video Foundation Models & Data for Multimodal Understanding
Awesome papers & datasets specifically focused on long-term videos.
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 Implementation of Video Swin Transformers for 3D Video Modeling
[NeurIPS'22] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
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*
[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
SoccerAct10 is a dataset which contains 10 different soccer actions. This dataset was developed using the videos from YouTube.
Trailers12k is a video movie trailer dataset composed of 12,000 titles associated to 10 genres. It distinguishes from other datasets by its collection procedure aiming to provide a high-quality publicly available dataset.
Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification
🧠️🖥️2️⃣️0️⃣️0️⃣️1️⃣️📽️👁️ The video:animation:anime category for AI2001, containing Aime video datasets
🧠️🖥️2️⃣️0️⃣️0️⃣️1️⃣️📽️
🧠️🖥️2️⃣️0️⃣️0️⃣️1️⃣️📽️🌳️ The video:nature category for AI2001, containing nature video datasets
🧠️🖥️2️⃣️0️⃣️0️⃣️1️⃣️📽️🕹️ The video:gameplay category for AI2001, containing gameplay video datasets
🧠️🖥️2️⃣️0️⃣️0️⃣️1️⃣️📽️📸️ The video:photography category for AI2001, containing photography video datasets
🧠️🖥️2️⃣️0️⃣️0️⃣️1️⃣️📽️ The video category for AI2001, containing video datasets
Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.
Tools for loading video dataset and transforms on video in pytorch. You can directly load video files without preprocessing.
Add a description, image, and links to the video-dataset topic page so that developers can more easily learn about it.
To associate your repository with the video-dataset topic, visit your repo's landing page and select "manage topics."