• Home
  • Search
  • Deep Attention-Based Spatially Recursive Networks for Fine-Grained Visual Recognition.
  • Cite Icon288
  • https://doi.org/10.1109/tcyb.2018.2813971Copy DOI Icon

Deep Attention-Based Spatially Recursive Networks for Fine-Grained Visual Recognition.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Fine-grained visual recognition is an important problem in pattern recognition applications. However, it is a challenging task due to the subtle interclass difference and large intraclass variation. Recent visual attention models are able to automatically locate critical object parts and represent them against appearance variations. However, without consideration of spatial dependencies in discriminative feature learning, these methods are underperformed in classifying fine-grained objects. In this paper, we present a deep attention-based spatially recursive model that can learn to attend to critical object parts and encode them into spatially expressive representations. Our network is technically premised on bilinear pooling, enabling local pairwise feature interactions between outputs from two different convolutional neural networks (CNNs) that correspond to distinct region detection and relevant feature extraction. Then, spatial long-short term memory (LSTMs) units are introduced to generate spatially meaningful hidden representations via the long-range dependency on all features in two dimensions. The attention model is leveraged between bilinear outcomes and spatial LSTMs for dynamic selection on varied inputs. Our model, which is composed of two-stream CNN layers, bilinear pooling, and spatial recursive encoding with attention, is end-to-end trainable to serve as the part detector and feature extractor whereby relevant features are localized, extracted, and encoded spatially for recognition purpose. We demonstrate the superiority of our method over two typical fine-grained recognition tasks: fine-grained image classification and person re-identification.

Similar Papers
  • PDF
  • Research Article
  • Citations9

Grouping Bilinear Pooling for Fine-Grained Image Classification

  • May 17, 2022
  • Applied Sciences
  • Rui Zeng +1
  • Research Article
  • Citations2

CNNAttLSTM: an attention-enhanced CNN–LSTM architecture for high-precision jackfruit leaf disease classification

  • Jan 05, 2026
  • Frontiers in Plant Science
  • Gaurav Tuteja +7
  • PDF
  • Research Article
  • Citations4

Detection and Localization of Audio Event for Home Surveillance Using CRNN

  • Dec 27, 2021
  • International Journal of Electronics and Telecommunications
  • V S Suruthhi +3
  • Conference Article
  • Citations66

Fine-grained classification via mixture of deep convolutional neural networks

  • Mar 01, 2016
  • Zongyuan Ge +5
  • PDF
  • Research Article
  • Citations106

An Efficient and Lightweight Convolutional Neural Network for Remote Sensing Image Scene Classification.

  • Apr 02, 2020
  • Sensors
  • Donghang Yu +5
  • Research Article
  • Citations38

Cultural Heritage and the Intelligent Internet of Things

  • Jun 13, 2019
  • Journal on Computing and Cultural Heritage
  • Woosik Lee +1
  • Dissertation

Genetic Programming for Fine-Grained Image Classification

  • Feb 23, 2026
  • Qinyu Wang
  • Conference Article
  • Citations8

Text-Embedded Bilinear Model for Fine-Grained Visual Recognition

  • Oct 12, 2020
  • Liang Sun +3
  • Conference Article
  • Citations15

Spatial Attentional Bilinear 3D Convolutional Network for Video-Based Autism Spectrum Disorder Detection

  • Apr 11, 2020
  • Kangbo Sun +4
  • Conference Article
  • Citations10

Simplified LSTM unit and search space probability exploration for image description

  • Dec 01, 2015
  • Oliver Nina +1
  • Research Article
  • Citations37

ECG-based cardiac arrhythmias detection through ensemble learning and fusion of deep spatial–temporal and long-range dependency features

  • Feb 24, 2024
  • Artificial Intelligence In Medicine
  • Sadia Din +4
  • Research Article
  • Citations3

MB-ConvLSTM: a novel hybrid deep learning model for accurate sign language recognition

  • Apr 28, 2025
  • International Journal of Web Information Systems
  • Shahad Thamear Ameen +4
  • Book Chapter
  • Citations1

Gujarati Task Oriented Dialogue Slot Tagging Using Deep Neural Network Models

  • Jan 01, 2021
  • Rachana Parikh +1
  • Research Article
  • Citations35

Temperature Forecasting for Stored Grain: A Deep Spatiotemporal Attention Approach

  • Dec 01, 2021
  • IEEE Internet of Things Journal
  • Shanshan Duan +4
  • Conference Article
  • Citations181

Fine-Grained Image Classification via Combining Vision and Language

  • Jul 01, 2017
  • Xiangteng He +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.