Partially Relevant Video Retrieval
3 papers with code • 3 benchmarks • 3 datasets
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.
Benchmarks
These leaderboards are used to track progress in Partially Relevant Video Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
ActivityNet Captions
Charades-STA
TVR
Most implemented papers
Partially Relevant Video Retrieval
HuiGuanLab/ms-sl
•
•
To fill the gap, we propose in this paper a novel T2VR subtask termed Partially Relevant Video Retrieval (PRVR).
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval
huiguanlab/dl-dkd
•
•
ICCV 2023
During the knowledge distillation, an inheritance student branch is devised to absorb the knowledge from the teacher model.
GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval
Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead.
