[ICCV 2021] MGSampler: An Explainable Sampling Strategy for Video Action Recognition
☆51Jul 9, 2022Updated 3 years ago
Alternatives and similar repositories for MGSampler
Users that are interested in MGSampler are comparing it to the libraries listed below
Sorting:
- Official PyTorch Implementation of Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition, ICCV 20…☆26Oct 15, 2021Updated 4 years ago
- Official PyTorch Implementation of paper EAN: Event Adaptive Network for Efficient Action Recognition https://arxiv.org/abs/2107.10771☆33Oct 24, 2023Updated 2 years ago
- [Codes of paper]: PAN: Towards Fast Action Recognition via Learning Persistence of Appearance☆104Aug 12, 2020Updated 5 years ago
- ☆16Jan 6, 2025Updated last year
- Tiny-VIRAT dataset. It will be available soon.☆18Sep 2, 2021Updated 4 years ago
- super image for action recognition☆56Mar 8, 2022Updated 3 years ago
- [CVPR 2022] An Empirical Study of End-to-end Temporal Action Detection☆86Feb 19, 2023Updated 3 years ago
- [NeurIPS 2022] PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points☆47Nov 24, 2023Updated 2 years ago
- Repository for the CVPR23 paper Re^2TAL☆13Nov 21, 2025Updated 3 months ago
- [CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition☆381Sep 17, 2022Updated 3 years ago
- BasicTAD: an Astounding RGB-Only Baselinefor Temporal Action Detection☆52Jun 10, 2023Updated 2 years ago
- ☆27Nov 26, 2018Updated 7 years ago
- ☆11Aug 22, 2018Updated 7 years ago
- ☆15Aug 1, 2019Updated 6 years ago
- Code for the paper "Disentangled Generative Models for Robust Prediction of System Dynamics"☆15May 2, 2023Updated 2 years ago
- [ECCV2020] Learn optimal resolution and skipping mechanism for efficient video understanding☆63Aug 17, 2020Updated 5 years ago
- ☆16Aug 5, 2022Updated 3 years ago
- Implementation of paper "Not All Frames Are Equal: Weakly-Supervised Video Grounding with Contextual Similarity and Visual Clustering Los…☆30Jun 29, 2020Updated 5 years ago
- ☆37Jul 8, 2018Updated 7 years ago
- 【AAAI'2021】MVFNet: Multi-View Fusion Network for Efficient Video Recognition☆134Mar 28, 2022Updated 3 years ago
- Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"☆117Jun 9, 2021Updated 4 years ago
- This is the official impletations of the EMNLP Findings paper, VideoINSTA: Zero-shot Long-Form Video Understanding via Informative Spatia…☆24Nov 15, 2024Updated last year
- [CVPR 2022] OCSampler: Compressing Videos to One Clip with Single-step Sampling☆17Jun 21, 2022Updated 3 years ago
- Code for ECCV 2020 paper "Hierarchical Visual-Textual Graph for Temporal Activity Localization via Language"☆17Aug 25, 2020Updated 5 years ago
- N-EPIC-Kitchens: The event-based camera extension of the large-scale EPIC-Kitchens dataset.☆23May 10, 2022Updated 3 years ago
- [ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, vi…☆241Aug 23, 2023Updated 2 years ago
- TAM: Temporal Adaptive Module for Video Recognition☆207Aug 18, 2022Updated 3 years ago
- Mutual Modality Learning code☆15Mar 1, 2021Updated 5 years ago
- ☆19May 1, 2025Updated 10 months ago
- ☆20Nov 29, 2021Updated 4 years ago
- SmallBigNet: Integrating Core and Contextual Views for Video Classification (CVPR2020)☆41Mar 10, 2022Updated 3 years ago
- Python script for downloading Kinetics datasets (Kinetics400, Kinetics600, Kinetics700)☆18Jun 8, 2020Updated 5 years ago
- [CVPRW2023] The official implementation of ETAD: A Unified Framework for Efficient Temporal Action Detection☆18Oct 3, 2024Updated last year
- ☆20Feb 27, 2023Updated 3 years ago
- [CVPR 2022] Cross-Architecture Self-supervised Video Representation Learning☆24Jul 5, 2022Updated 3 years ago
- Official implementation of BGNN(CVPR 2021)☆20Jul 12, 2021Updated 4 years ago
- [Findings of EMNLP 2022] AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant☆23Sep 11, 2023Updated 2 years ago
- Two-Stream Convolutional Networks for Action Recognition in Videos☆21Oct 5, 2021Updated 4 years ago
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆127Dec 15, 2024Updated last year