UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.
☆236Apr 15, 2024Updated last year
Alternatives and similar repositories for UMT
Users that are interested in UMT are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2021] Moment-DETR code and QVHighlights dataset☆343Apr 18, 2024Updated last year
- Official pytorch repository for "QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection" (CVPR 2023 …☆246Aug 12, 2025Updated 6 months ago
- Official pytorch repository for CG-DETR "Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Gr…☆149Aug 21, 2024Updated last year
- Implementation of Cross-category Video Highlight Detection via Set-based Learning (ICCV 2021).☆79Aug 27, 2021Updated 4 years ago
- [CVPR 2024] Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection☆114Jul 17, 2024Updated last year
- Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"☆117Jun 9, 2021Updated 4 years ago
- 📦 A lightweight machine learning toolkit for researchers, providing common model design & learning functionalities.☆28Jul 2, 2025Updated 8 months ago
- Official pytorch implementation of "Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding …☆42Aug 5, 2022Updated 3 years ago
- [ICCV 2023] UniVTG: Towards Unified Video-Language Temporal Grounding☆375May 8, 2024Updated last year
- [ECCV 22] LocVTP: Video-Text Pre-training for Temporal Localization☆39Jul 29, 2022Updated 3 years ago
- 前沿论文持续更新--视频时刻定位 or 时域语言定位 or 视频片段检索。☆261Aug 26, 2023Updated 2 years ago
- ☆14Oct 30, 2023Updated 2 years ago
- ☆36Apr 14, 2021Updated 4 years ago
- End-to-end Multi-modal Video Temporal Grounding, NeurIPS 2021☆18Oct 24, 2021Updated 4 years ago
- Official pytorch repository for "Knowing Where to Focus: Event-aware Transformer for Video Grounding" (ICCV 2023)☆55Sep 7, 2023Updated 2 years ago
- [NeurIPS 2022] Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding☆53Mar 5, 2024Updated last year
- [CVPR 2022 Oral] TubeDETR: Spatio-Temporal Video Grounding with Transformers☆193Sep 24, 2023Updated 2 years ago
- [CVPR 2024 Accepted] TaskWeave: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection☆29Sep 26, 2024Updated last year
- ☆80Nov 24, 2024Updated last year
- "Video Moment Retrieval from Text Queries via Single Frame Annotation" in SIGIR 2022☆69Jun 27, 2022Updated 3 years ago
- Official Implementation of "Chrono: A Simple Blueprint for Representing Time in MLLMs"☆92Mar 9, 2025Updated 11 months ago
- ☆56Oct 30, 2015Updated 10 years ago
- Code for ECCV 2022 paper "Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding"☆29May 31, 2023Updated 2 years ago
- Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-based Active Learning☆15Dec 12, 2023Updated 2 years ago
- [AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding☆91Nov 16, 2022Updated 3 years ago
- [ECCV 2020] PyTorch code for XML on TVRetrieval dataset - TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval☆161May 28, 2024Updated last year
- Video Corpus Moment Retrieval with Contrastive Learning (SIGIR 2021)☆57Aug 31, 2021Updated 4 years ago
- MomentDiff: Generative Video Moment Retrieval from Random to Real--NeurIPS 2023☆80Nov 2, 2023Updated 2 years ago
- Code for the paper "Zero-shot Natural Language Video Localization" (ICCV2021, Oral).☆48Mar 15, 2023Updated 2 years ago
- Span-based Localizing Network for Natural Language Video Localization (ACL 2020)☆112Oct 15, 2021Updated 4 years ago
- The HC-STVG Dataset☆62Apr 12, 2023Updated 2 years ago
- MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions☆172Oct 22, 2023Updated 2 years ago
- Repository of proposal-free temporal moment localization work☆33Jun 11, 2024Updated last year
- Hierarchical Video-Moment Retrieval and Step-Captioning (CVPR 2023)☆107Jan 23, 2025Updated last year
- [2021 MultiMedia] CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval☆42Sep 23, 2021Updated 4 years ago
- Temporal Sentence Grounding in Videos / Natural Language Video Localization / Video Moment Retrieval的相关工作☆30Mar 4, 2022Updated 3 years ago
- ☆16Dec 4, 2024Updated last year
- Repository for the CVPR-20 paper "Local-Global Video-Text Interactions for Temporal Grounding"☆131Jul 5, 2021Updated 4 years ago
- TALL: Temporal Activity Localization via Language Query☆217Mar 15, 2018Updated 7 years ago