ActivityNet Captions

doi:doi:10.57702/lxpldj5v

ActivityNet Captions

The ActivityNet Captions is a benchmark dataset proposed for dense video captioning. There are 20K untrimmed videos in total, and each video has several annotated segments with starting and ending times as well as the associated captions.

BibTex:

@dataset{Ranjay_Krishna_and_Kenji_Hata_and_Frederic_Ren_and_Li_Fei-Fei_and_Juan_Carlos_Niebles_2024,
    abstract = {The ActivityNet Captions is a benchmark dataset proposed for dense video captioning. There are 20K untrimmed videos in total, and each video has several annotated segments with starting and ending times as well as the associated captions.},
    author = {Ranjay Krishna and Kenji Hata and Frederic Ren and Li Fei-Fei and Juan Carlos Niebles},
    doi = {10.57702/lxpldj5v},
    institution = {No Organization},
    keyword = {'ActivityNet', 'Captions', 'Text Retrieval', 'Video Description', 'Video Moment Retrieval', 'activitynet', 'activitynet captions', 'annotated segments', 'captions', 'dense video captioning', 'natural language video grounding', 'retrieval', 'temporal activity localization', 'text', 'text-to-video retrieval', 'untrimmed videos', 'video', 'video analysis', 'video classification', 'video grounding'},
    month = {dec},
    publisher = {TIB},
    title = {ActivityNet Captions},
    url = {https://service.tib.eu/ldmservice/dataset/activitynet-captions},
    year = {2024}
}