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.
Gramian Multimodal Representation Learning and Alignment
Generative Semantic Communication: Architectures, Technologies, and Applications
Multi-Scale Contrastive Learning for Video Temporal Grounding
Multimodal Contextualized Support for Enhancing Video Retrieval System
Video LLMs for Temporal Reasoning in Long Videos
CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives
VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
SimBase: A Simple Baseline for Temporal Video Grounding
ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising
Generating Signed Language Instructions in Large-Scale Dialogue Systems
Beyond Coarse-Grained Matching in Video-Text Retrieval
MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval
Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval
VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding
Transformer with Controlled Attention for Synchronous Motion Captioning
Unfolding Videos Dynamics via Taylor Expansion
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets
T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval
MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval
NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality
Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach
Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses
Neural Graph Matching for Video Retrieval in Large-Scale Video-driven E-commerce
ExpertAF: Expert Actionable Feedback from Video
Learning Video Context as Interleaved Multimodal Sequences
SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval
EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.