TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/QVHighlights

QVHighlights

Query-based Video Highlights

TextsVideosAttribution-NonCommercial-ShareAlike 4.0 InternationalIntroduced 2021-07-20

The Query-based Video Highlights (QVHighlights) dataset is a dataset for detecting customized moments and highlights from videos given natural language (NL). It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips.

Benchmarks

16k/mAP16k/Hit@1Highlight Detection/mAPHighlight Detection/Hit@1Moment Retrieval/mAPMoment Retrieval/R@1 IoU=0.5Moment Retrieval/R@1 IoU=0.7Moment Retrieval/mAP@0.5Moment Retrieval/mAP@0.75Moment Retrieval/R1@0.5Moment Retrieval/R1@0.7Video/R@1,IoU=0.7Video/R@1,IoU=0.5Video Grounding/R@1,IoU=0.7Video Grounding/R@1,IoU=0.5Video Retrieval/R@1,IoU=0.7Video Retrieval/R@1,IoU=0.5

Statistics

Papers
41
Benchmarks
17

Links

Homepage

Tasks

16kHighlight DetectionMoment RetrievalVideoVideo GroundingVideo RetrievalZero-shot Moment Retrieval