Skip to Main content Skip to Navigation
Poster communications

Describe me if you can! Characterized instance-level human parsing

Abstract : Several computer vision applications as person search or online fashion rely on human description. The use of instance-level human parsing (HP) is therefore relevant since it localizes semantic attributes and body parts within a person. But how to characterize these attributes? To our knowledge, only some single-HP datasets describe attributes with some color, size and/or pattern characteristics. There is a lack of dataset for multi-HP in the wild with such characteristics. In this article, we propose the dataset CCIHP based on the multi-HP dataset CIHP, with 20 new labels covering these 3 kinds of characteristics. In addition, we propose HPTR, a new bottom-up multi-task method based on transformers as a fast baseline, to encourage research for fast and accurate methods of precise human descriptions.
Complete list of metadata
Contributor : Contributeur MAP CEA Connect in order to contact the contributor
Submitted on : Thursday, May 5, 2022 - 7:00:07 PM
Last modification on : Saturday, May 7, 2022 - 3:39:45 AM
Long-term archiving on: : Saturday, August 6, 2022 - 6:47:45 PM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2022-11-01

Please log in to resquest access to the document



Angélique Loesch, Romaric Audigier. Describe me if you can! Characterized instance-level human parsing. ICIP 2021 - IEEE International Conference on Image Processing, Sep 2021, Anchorage, United States. 2021, pp.2528-2532, 2021, 2021 IEEE International Conference on Image Processing (ICIP). ⟨10.1109/ICIP42928.2021.9506509⟩. ⟨cea-03660437⟩



Record views