YouTube Co-localization Dataset (ECCV + IEEE Trans. CSVT papers) [GEU and NTU]

by No License

YouTube Co-localization Dataset (ECCV + IEEE Trans. CSVT papers) [GEU and NTU]

The dataset consists of bounding box annotations for 15k frames of videos collected from YouTube Objects Dataset.If you find this dataset useful, kindly cite the following papers:[1] Koteswar Rao Jerripothula, Jianfei Cai, and Junsong Yuan, “Efficient Video Object Co-localization with Co-saliency Activated Tracklets” in IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2018.[2] Koteswar Rao Jerripothula, Jianfei Cai, and Junsong Yuan, “CATS: Co-saliency Activated Tracklet Selection for Video Co-localization” in European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 2016.

Dataset Attributes

Label SVG
CategoriesCo-Localization, Co-Saliency, Video, Cats, Tracklet, Benchmark, Binary, Object, Retrieval, Similarity, Tracking, Matching, Localization