https://github.com/minjoong507/MPGN
공식 코드Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval
Papers with Code 아카이브
Moment Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 57
Moment retrieval can de defined as the task of "localizing moments in a video given a user query".
Description from: QVHIGHLIGHTS: Detecting Moments and Highlights in Videos via Natural Language Queries
Image credit: QVHIGHLIGHTS: Detecting Moments and Highlights in Videos via Natural Language Queries
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/minjoong507/bm-detr
공식 코드Background-aware Moment Detection for Video Moment Retrieval
https://github.com/niluthpol/weak_supervised_video_moment
공식 코드https://github.com/opengvlab/internvideo
공식 코드InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
https://github.com/opengvlab/internvideo2
공식 코드InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
https://github.com/opengvlab/video-mamba-suite
공식 코드Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
https://github.com/qingchen239/ld-detr
공식 코드LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection
https://github.com/r-cui/ViGA
공식 코드Video Moment Retrieval from Text Queries via Single Frame Annotation
https://github.com/ranking-vmr/spr
공식 코드https://github.com/ranking-vmr/tvr-ranking
공식 코드TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries
https://github.com/showlab/univtg
공식 코드https://github.com/sjpark5800/la-detr
공식 코드https://github.com/skyline-9/visionary-vids
공식 코드Joint Moment Retrieval and Highlight Detection Via Natural Language Queries
https://github.com/sming256/timeloc
공식 코드TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
https://github.com/sudo-Boris/mr-Blip
공식 코드The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval
https://github.com/swordlidev/LLaVA-MR
공식 코드LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
https://github.com/tanghaoyu258/ACRM-for-moment-retrieval
공식 코드https://github.com/tencentarc/umt
공식 코드UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
https://github.com/visualaikhu/keyword-detr
공식 코드https://github.com/wjun0830/cgdetr
공식 코드Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding
https://github.com/wjun0830/qd-detr
공식 코드Query-Dependent Video Representation for Moment Retrieval and Highlight Detection
https://github.com/yeliudev/R2-Tuning
공식 코드R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding
https://github.com/yingsen1/unimd
공식 코드UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection
https://github.com/yny0506/massive-videos-moment-retrieval
공식 코드https://github.com/yongliang-wu/numpro
공식 코드https://github.com/zhouhaocv/dtg-spl
공식 코드Towards Diverse Temporal Grounding under Single Positive Labels
https://github.com/zhuo-cao/flashvtg
공식 코드FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
https://github.com/zxccade/shine
공식 코드SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
https://gitlab.com/grounded-sport-convai/goal-baselines
공식 코드Going for GOAL: A Resource for Grounded Football Commentaries
https://github.com/IsaacChanghau/ReLoCLNet
https://github.com/MS-P3/code7/tree/main/umt5
UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
https://github.com/Mathux/TMR
TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis
https://github.com/MindCode-4/code-5/tree/main/umt5
UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
https://github.com/OpenGVLab/TimeSuite
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
https://github.com/Soldelli/VLG-Net
VLG-Net: Video-Language Graph Matching Network for Video Grounding
https://github.com/escorciav/moments-retrieval-page
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.