Attribute Recognition from Adaptive Parts

07/05/2016
by   Luwei Yang, et al.
0

Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep learning approach to overcome the limitation. It generates object parts from key points and perform attribute recognition accordingly, allowing adaptive spatial transform of the parts. Both key point estimation and attribute recognition are learnt jointly in a multi-task setting. Extensive experiments on two datasets verify the efficacy of proposed end-to-end approach.

READ FULL TEXT

page 2

page 3

page 7

page 9

research
03/15/2023

An End-to-End Multi-Task Learning Model for Image-based Table Recognition

Image-based table recognition is a challenging task due to the diversity...
research
08/09/2019

Recognizing Part Attributes with Insufficient Data

Recognizing attributes of objects and their parts is important to many c...
research
11/13/2020

Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints

Pedestrian Attribute Recognition (PAR) has aroused extensive attention d...
research
07/19/2017

Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model

Pedestrian attribute inference is a demanding problem in visual surveill...
research
09/16/2023

Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints

We propose a first step toward multilingual end-to-end automatic speech ...
research
09/25/2017

Attribute Recognition by Joint Recurrent Learning of Context and Correlation

Recognising semantic pedestrian attributes in surveillance images is a c...
research
08/03/2022

Compressive Self-localization Using Relative Attribute Embedding

The use of relative attribute (e.g., beautiful, safe, convenient) -based...

Please sign up or login with your details

Forgot password? Click here to reset