A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification

Abstract

In recent years, attention models have been extensively used for person and vehicle re-identification. Most re-identification methods are designed to focus attention on key-point locations. However, depending on the orientation, the contribution of each key-point varies. In this paper, we present a novel dual-path adaptive attention model for vehicle re-identification (AAVER).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 27, 2019
Accession Number
AD1153060

Entities

People

  • Amit Kumar
  • Jun-Cheng Chen
  • Neehar Peri
  • Pirazh Khorramshahi
  • Rama Chellappa
  • Sai Saketh Rambhatla

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Computer Vision
  • Computers
  • Convolutional Neural Networks
  • Detection
  • Dimensionality Reduction
  • Distance Learning
  • Feature Extraction
  • Identification
  • Image Processing
  • Image Recognition
  • Information Science
  • Information Systems
  • Intelligence Community (United States)
  • Learning
  • Neural Networks
  • Orientation (Direction)
  • Pattern Recognition
  • Recognition
  • Supervised Machine Learning

Fields of Study

  • Engineering

Readers

  • Computer Vision.
  • Nanofabrication and Microfabrication.
  • Theoretical Analysis.