Papers with Code 아카이브
Video Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 19
- 보존된 평가 기록
- 308
The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query. Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
vid-TLDR: Training Free Token merging for Light-weight Video Transformer
HawkEye: Training Video-Text LLMs for Grounding Text in Videos
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval
Event-aware Video Corpus Moment Retrieval
Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
Point-VOS: Pointing Up Video Object Segmentation
Video Editing for Video Retrieval
M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval
Multi-granularity Correspondence Learning from Long-term Noisy Videos
CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing
DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
Distilling Vision-Language Models on Millions of Videos
Text-Video Retrieval via Variational Multi-Modal Hypergraph Networks
Context-Guided Spatio-Temporal Video Grounding
Detours for Navigating Instructional Videos
Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning
Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding
LLM4VG: Large Language Models Evaluation for Video Grounding
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision
ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
WAVER: Writing-style Agnostic Text-Video Retrieval via Distilling Vision-Language Models Through Open-Vocabulary Knowledge
Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval
Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval
Grounded Question-Answering in Long Egocentric Videos
RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning
EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
RTQ: Rethinking Video-language Understanding Based on Image-text Model
Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval
VTimeLLM: Empower LLM to Grasp Video Moments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.