- P
VALUE Dataset
- paperswithcode.com
- library.toponeai.link
Updated Apr 21, 2024
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteLinjie Li; Jie Lei; Zhe Gan; Licheng Yu; Yen-Chun Chen; Rohit Pillai; Yu Cheng; Luowei Zhou; Xin Eric Wang; William Yang Wang; Tamara Lee Berg; Mohit Bansal; Jingjing Liu; Lijuan Wang; Zicheng Liu (2024). VALUE Dataset [Dataset]. https://paperswithcode.com/dataset/valueDataset updatedApr 21, 2024AuthorsLinjie Li; Jie Lei; Zhe Gan; Licheng Yu; Yen-Chun Chen; Rohit Pillai; Yu Cheng; Luowei Zhou; Xin Eric Wang; William Yang Wang; Tamara Lee Berg; Mohit Bansal; Jingjing Liu; Lijuan Wang; Zicheng LiuDescriptionVALUE is a Video-And-Language Understanding Evaluation benchmark to test models that are generalizable to diverse tasks, domains, and datasets. It is an assemblage of 11 VidL (video-and-language) datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. Rather than focusing on single-channel videos with visual information only, VALUE promotes models that leverage information from both video frames and their associated subtitles, as well as models that share knowledge across multiple tasks.
The datasets used for the VALUE benchmark are: TVQA, TVR, TVC, How2R, How2QA, VIOLIN, VLEP, YouCook2 (YC2C, YC2R), VATEX
- O
VALUE (Video-And-Language Understanding Evaluation)
- opendatalab.com
zipUpdated Sep 22, 2022ShareFacebookTwitterEmailClick to copy linkLink copiedCiteUniversity of California, Santa Barbara (2022). VALUE (Video-And-Language Understanding Evaluation) [Dataset]. https://opendatalab.com/OpenDataLab/VALUEzipAvailable download formatsDataset updatedSep 22, 2022Dataset provided byUniversity of California, Santa Barbara
Microsoft
Tsinghua University
University of North Carolina at Chapel Hill
University of California, Santa CruzLicenseAttribution-NonCommercial-ShareAlike 4.0 (CC BY-NC-SA 4.0)https://creativecommons.org/licenses/by-nc-sa/4.0/
License information was derived automaticallyDescriptionVALUE is a Video-And-Language Understanding Evaluation benchmark to test models that are generalizable to diverse tasks, domains, and datasets. It is an assemblage of 11 VidL (video-and-language) datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. Rather than focusing on single-channel videos with visual information only, VALUE promotes models that leverage information from both video frames and their associated subtitles, as well as models that share knowledge across multiple tasks. The datasets used for the VALUE benchmark are: TVQA, TVR, TVC, How2R, How2QA, VIOLIN, VLEP, YouCook2 (YC2C, YC2R), VATEX
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailVALUE is a Video-And-Language Understanding Evaluation benchmark to test models that are generalizable to diverse tasks, domains, and datasets. It is an assemblage of 11 VidL (video-and-language) datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. Rather than focusing on single-channel videos with visual information only, VALUE promotes models that leverage information from both video frames and their associated subtitles, as well as models that share knowledge across multiple tasks.
The datasets used for the VALUE benchmark are: TVQA, TVR, TVC, How2R, How2QA, VIOLIN, VLEP, YouCook2 (YC2C, YC2R), VATEX