SOTAVerified

Partially Relevant Video Retrieval

In the Partially Relevant Video Retrieval (PRVR) task, an untrimmed video is considered to be partially relevant w.r.t. a given textual query if it contains a moment relevant to the query. PRVR aims to retrieve such partially relevant videos from a large collection of untrimmed videos.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–8 of 8 papers

TitleStatusHype
Partially Relevant Video RetrievalCode1
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video RetrievalCode1
GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video RetrievalCode1
GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video RetrievalCode1
Towards Efficient Partially Relevant Video Retrieval with Active Moment DiscoveringCode0
Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval—0
Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval—0
Event-aware Video Corpus Moment Retrieval—0
Show:102550

No leaderboard results yet.