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/Huntersxsx/MGPN
공식 코드You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos
https://github.com/Pilhyeon/BAM-DETR
공식 코드BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos
https://github.com/Soldelli/MAD
공식 코드MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions
https://github.com/Xun-Yang/Causal_Video_Moment_Retrieval
공식 코드Deconfounded Video Moment Retrieval with Causal Intervention
https://github.com/YoucanBaby/VTG-GPT
공식 코드VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT
https://github.com/ai-forever/sg-detr
공식 코드Saliency-Guided DETR for Moment Retrieval and Highlight Detection
https://github.com/baopj/vid-morp
공식 코드Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the Wild
https://github.com/dbstjswo505/SQuiDNet
공식 코드Selective Query-guided Debiasing for Video Corpus Moment Retrieval
https://github.com/divraz/TaskSegmentation
공식 코드Language-Conditioned Change-point Detection to Identify Sub-Tasks in Robotics Domains
https://github.com/dmgcsilva/mmplanllm
공식 코드Show and Guide: Instructional-Plan Grounded Vision and Language Model
https://github.com/dpaul06/VideoLights
공식 코드https://github.com/eanson023/mlp
공식 코드MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions
https://github.com/easonxiao-888/uvcom
공식 코드https://github.com/edengabriel/taskweave
공식 코드https://github.com/fletcherjiang/llmepet
공식 코드Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
https://github.com/frostinassiky/denoiseloc
공식 코드https://github.com/google-research/scenic
공식 코드https://github.com/gyxxyg/vtg-llm
공식 코드VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding
https://github.com/hdy007007/prem
공식 코드Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
https://github.com/hlchen23/verified
공식 코드VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
https://github.com/houzhijian/conquer
공식 코드CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval
https://github.com/ikuinen/CMIN
공식 코드Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos
https://github.com/ikuinen/regularized_two-branch_proposal_network
공식 코드Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos
https://github.com/imccretrieval/momentdiff
공식 코드MomentDiff: Generative Video Moment Retrieval from Random to Real
https://github.com/j-min/HiREST
공식 코드https://github.com/jayleicn/TVCaption
공식 코드TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval
https://github.com/jayleicn/TVRetrieval
공식 코드TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval
https://github.com/jayleicn/mTVRetrieval
공식 코드https://github.com/jayleicn/moment_detr
공식 코드QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries
https://github.com/keflanagan/momentofuntruth
공식 코드Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval
https://github.com/line/lighthouse
공식 코드Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection
https://github.com/linjieli222/HERO
공식 코드HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
https://github.com/lntzm/mesm
공식 코드Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval
https://github.com/love481/Cross-modal-Contrastive-Learning-with-Asymmetric-Co-attention-Network-for-Video-Moment-Retrieval
공식 코드Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval
https://github.com/mingyao1120/tr-detr
공식 코드TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.