Advertisement

Topics

Uniform and Variational Deep Learning for RGB-D Object Recognition and Person Re-Identification.

08:00 EDT 15th May 2019 | BioPortfolio

Summary of "Uniform and Variational Deep Learning for RGB-D Object Recognition and Person Re-Identification."

In this paper, we propose a uniform and variational deep learning (UVDL) method for RGB-D object recognition and person re-identification. Unlike most existing object recognition and person re-identification methods which usually only use the visual appearance information from RGB images, our method recognizes visual objects and persons with RGB-D images to exploit more reliable information such as geometric and anthropometric information which are robust to different viewpoints. Specifically, we extract the depth feature and the appearance feature from the depth and RGB images with two deep convolutional neural networks, respectively. In order to combine the depth feature and the appearance feature to exploit their relationship, we design a uniform and variational multimodal auto-encoder at the top layer of our deep network to seek a uniform latent variable by projecting them into a common space, which contains the whole information of RGB-D images and has small intra-class variation and large inter-class variation, simultaneously. Finally, we optimize the auto-encoder layer and two deep convolutional neural networks jointly to minimize the discriminative loss and the reconstruction error. Experimental results on both RGB-D object recognition and RGB-D person reidentification are presented to show the efficiency of our proposed approach.

Affiliation

Journal Details

This article was published in the following journal.

Name: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
ISSN: 1941-0042
Pages:

Links

DeepDyve research library

PubMed Articles [13269 Associated PubMed Articles listed on BioPortfolio]

Deep Representation Learning with Part Loss for Person Re-Identification.

Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID). Most of current approaches learn deep representations in classification tasks, which e...

Beyond core object recognition: Recurrent processes account for object recognition under occlusion.

Core object recognition, the ability to rapidly recognize objects despite variations in their appearance, is largely solved through the feedforward processing of visual information. Deep neural networ...

EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes.

Big data has had a great share in the success of deep learning in computer vision. Recent works suggest that there is significant further potential to increase object detection performance by utilizin...

Cross-task perceptual learning of object recognition in simulated retinal implant perception.

The perception gained by retina implants (RI) is limited, which asks for a learning regime to improve patients' visual perception. Here we simulated RI vision and investigated if object recognition in...

Cross-task perceptual learning of object recognition in simulated retinal implant perception.

The perception gained by retina implants (RI) is limited, which asks for a learning regime to improve patients' visual perception. Here we simulated RI vision and investigated if object recognition in...

Clinical Trials [5066 Associated Clinical Trials listed on BioPortfolio]

Effects of Transcranial Magnetic Stimulation on Object Recognition

Background: - The brain has natural rhythms called brain waves. An electroencephalogram (EEG) can record these rhythms. When people identify the picture of a familiar object shown on a co...

Multi-center Database Registry to Study Thalamus Changes Using AI in MS

In this study the Investigator's propose to validate a newly developed approach, DeepGRAI (Deep Gray Rating via Artificial Intelligence), to simplify the calculation of thalamic atrophy in...

Identification of Clinically Occult Glioma Cells and Characterization of Glioma Behavior Through Machine Learning Analysis of Advanced Imaging Technology

Gliomas are one of the most challenging tumors to treat, because areas of the apparently normal brain contain microscopic deposits of glioma cells; indeed, these occult cells are known to ...

Deep-learning Based Location of Spine CT

CT-guided epidural steroid injection (ESI) thrives among interventional radiologists. Although X-ray fluoroscopy still remains as the gold standard to guide ESI, CT guidance has the merits...

Bedside Ultrasound in the Assessment of Deep Venous Thrombosis: Effectiveness of In-Person Versus Online Instruction

This study will examine the effectiveness of pre-recorded instructional videos in the use of bedside ultrasonography to ascertain the presence of a lower extremity deep venous thrombosis (...

Medical and Biotech [MESH] Definitions

Process in which individuals take the initiative, in diagnosing their learning needs, formulating learning goals, identifying resources for learning, choosing and implementing learning strategies and evaluating learning outcomes (Knowles, 1975)

Recognition and discrimination of the heaviness of a lifted object.

Mental activity, not predominantly perceptual, by which one apprehends some aspect of an object or situation based on past learning and experience.

Attachment, conscious or unconscious, of emotional feeling and significance to an idea, object or most commonly a person.

A method of differentiating individuals based on the analysis of qualitative or quantitative biological traits or patterns. This process which has applications in forensics and identity theft prevention includes DNA profiles or DNA fingerprints, hand fingerprints, automated facial recognition, iris scan, hand geometry, retinal scan, vascular patterns, automated voice pattern recognition, and ultrasound of fingers.

Advertisement
Quick Search
Advertisement
Advertisement

 


DeepDyve research library

Searches Linking to this Article