Occluded Video Instance Segmentation

doi:doi:10.57702/dx5t2axm

Occluded Video Instance Segmentation

Occluded video instance segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to occluded video instance segmentation with high-resolution input features poses significant challenges, often leading to insufficient GPU memory capacity.

BibTex:

@dataset{Jiyang_Qi_and_Yan_Gao_and_Yao_Hu_and_Xinggang_Wang_and_Xiaoyu_Liu_and_Xiang_Bai_and_Serge_Belongie_and_Alan_Yuille_and_Philip_HS_Torr_and_Song_Bai_2024,
    abstract = {Occluded video instance segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to occluded video instance segmentation with high-resolution input features poses significant challenges, often leading to insufficient GPU memory capacity.},
    author = {Jiyang Qi and Yan Gao and Yao Hu and Xinggang Wang and Xiaoyu Liu and Xiang Bai and Serge Belongie and Alan Yuille and Philip HS Torr and Song Bai},
    doi = {10.57702/dx5t2axm},
    institution = {No Organization},
    keyword = {'axial-trajectory attention', 'occluded video instance segmentation', 'temporal consistency'},
    month = {dec},
    publisher = {TIB},
    title = {Occluded Video Instance Segmentation},
    url = {https://service.tib.eu/ldmservice/dataset/occluded-video-instance-segmentation},
    year = {2024}
}