v-iashin / video_features
Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.
☆536Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for video_features
- Code release for ActionFormer (ECCV 2022)☆444Updated 7 months ago
- Temporal Action Detection & Weakly Supervised Temporal Action Detection & Temporal Action Proposal Generation☆443Updated last week
- Easy to use video deep features extractor☆309Updated 4 years ago
- ☆778Updated 6 months ago
- This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"☆518Updated 11 months ago
- PyTorch implementation of a collections of scalable Video Transformer Benchmarks.☆283Updated 2 years ago
- Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)☆226Updated last year
- [CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking☆520Updated last month
- Code for I3D Feature Extraction☆138Updated 5 years ago
- Implementation of ViViT: A Video Vision Transformer☆516Updated 3 years ago
- A curated list of temporal action localization/detection and related area (e.g. temporal action proposal) resources.☆572Updated 2 years ago
- Release of the pretrained S3D Network in PyTorch (ECCV 2018)☆127Updated last year
- This is the pytorch implementation of some representative action recognition approaches including I3D, S3D, TSN and TAM.☆244Updated 3 years ago
- [ICCV2023] UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer☆294Updated 7 months ago
- [CVPR2023] Code for the paper, TriDet: Temporal Action Detection with Relative Boundary Modeling☆165Updated 10 months ago
- MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;☆257Updated 2 years ago
- Effective Video Augmentation Techniques for Training Convolutional Neural Networks☆388Updated 9 months ago
- Extracting optical flow and frames☆307Updated 2 years ago
- PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.☆86Updated 3 years ago
- [NeurIPS 2021] Moment-DETR code and QVHighlights dataset☆271Updated 7 months ago
- Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.☆451Updated last year
- Multi-Modal Transformer for Video Retrieval☆258Updated last month
- ☆980Updated 4 years ago
- End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)☆208Updated 10 months ago
- UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or …☆193Updated 7 months ago
- Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]☆351Updated 2 years ago
- A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is ac…☆291Updated 2 years ago
- OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.☆187Updated last month
- Research code for CVPR 2022 paper "SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning"☆237Updated 2 years ago
- Official repo for BMVC2021 paper ASFormer: Transformer for action segmentation☆94Updated 2 years ago