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.
☆593Updated 3 months ago
Alternatives and similar repositories for video_features:
Users that are interested in video_features are comparing it to the libraries listed below
- Code release for ActionFormer (ECCV 2022)☆486Updated last year
- Temporal Action Detection & Weakly Supervised Temporal Action Detection & Temporal Action Proposal Generation☆491Updated this week
- Easy to use video deep features extractor☆315Updated 4 years ago
- Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)☆227Updated 2 years ago
- Code for I3D Feature Extraction☆147Updated 5 years ago
- [CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking☆629Updated 7 months ago
- This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"☆551Updated last year
- ☆847Updated 11 months ago
- ☆1,007Updated 4 years ago
- PyTorch implementation of a collections of scalable Video Transformer Benchmarks.☆295Updated 3 years ago
- Effective Video Augmentation Techniques for Training Convolutional Neural Networks☆403Updated last year
- Implementation of ViViT: A Video Vision Transformer☆531Updated 3 years ago
- A curated list of deep learning resources for video-text retrieval.☆618Updated last year
- This is the pytorch implementation of some representative action recognition approaches including I3D, S3D, TSN and TAM.☆248Updated 3 years ago
- [NeurIPS 2021] Moment-DETR code and QVHighlights dataset☆304Updated last year
- A curated list of temporal action localization/detection and related area (e.g. temporal action proposal) resources.☆577Updated 2 years ago
- A curated list of awesome temporal action segmentation resources.☆198Updated last year
- Release of the pretrained S3D Network in PyTorch (ECCV 2018)☆131Updated last year
- OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.☆251Updated last week
- An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"☆936Updated last year
- [ICCV2023] UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer☆312Updated last year
- Inflated i3d network with inception backbone, weights transfered from tensorflow☆544Updated 11 months ago
- UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or …☆212Updated last year
- MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;☆269Updated 2 years ago
- [TIP 2022] End-to-end Temporal Action Detection with Transformer☆153Updated 2 years ago
- A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is ac…☆296Updated 3 years ago
- Official repo for BMVC2021 paper ASFormer: Transformer for action segmentation☆106Updated 3 years ago
- Extracting optical flow and frames☆313Updated 3 years ago
- PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.☆86Updated 3 years ago
- An official implementation for " UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation"☆353Updated 9 months ago