Describe me if you can! Characterized instance-level human parsing - Archive ouverte HAL Access content directly
Conference Poster Year : 2021

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

(1) , (1)
1

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.
Fichier principal
Vignette du fichier
Human_parsing_CIHP__2.pdf (1.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

cea-03660437 , version 1 (05-05-2022)

Identifiers

Cite

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⟩
10 View
4 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More