Sorry, you need to enable JavaScript to visit this website.

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

Primary tabs

Citation Author(s):
Angelique Loesch, Romaric Audigier
Submitted by:
Angelique Loesch
Last updated:
15 October 2021 - 11:09am
Document Type:
Presentation Slides
Document Year:
2021
Event:
Presenters Name:
Angelique Loesch
Paper Code:
2347

Abstract 

Abstract: 

Several computer vision applications such 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 characteristics1. In addition, we propose HPTR, a new bottom-up multi-task method based on transformers as a fast and scalable baseline. It is the fastest method of multi-HP state of the art while having precision comparable to the most precise bottom-up method. We hope this will encourage research for fast and accurate methods of precise human descriptions. 1 CCIHP is available on https://kalisteo.cea.fr/index.php/free-resources/

up
0 users have voted:

Dataset Files

presentation of the article

(23)