TencentARC / UMT
UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.
☆206Updated 11 months ago
Alternatives and similar repositories for UMT:
Users that are interested in UMT are comparing it to the libraries listed below
- [NeurIPS 2021] Moment-DETR code and QVHighlights dataset☆296Updated 11 months ago
- Official pytorch repository for "QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection" (CVPR 2023 …☆224Updated last year
- Official pytorch repository for CG-DETR "Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Gr…☆127Updated 7 months ago
- https://layer6ai-labs.github.io/xpool/☆122Updated last year
- [arXiv22] Disentangled Representation Learning for Text-Video Retrieval☆96Updated 2 years ago
- Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"☆107Updated 3 years ago
- [ECCV2022] A pytorch implementation for TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval☆75Updated 2 years ago
- Hierarchical Video-Moment Retrieval and Step-Captioning (CVPR 2023)☆100Updated 2 months ago
- ☆243Updated 2 years ago
- Official code for "Bridging Video-text Retrieval with Multiple Choice Questions", CVPR 2022 (Oral).☆138Updated 2 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。☆248Updated last year
- 🌀 R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding (ECCV 2024)☆80Updated 8 months ago
- End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)☆217Updated last year
- An official implementation for "X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval"☆153Updated 11 months ago
- ☆192Updated 2 years ago
- Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]