Skip to Content

9 Results Found

  • Article
  • Open Access
2 Citations
1,949 Views
13 Pages

TRM-ViT: A Tiny Recursive Vision Transformer for Efficient Melanoma Detection

  • My Abdelouahed Sabri,
  • Ali Belkhiri,
  • Abla Rahmouni and
  • Abdellah Aarab

Melanoma remains one of the most aggressive forms of skin cancer, and its early detection is critical for improving patient survival. Vision Transformers (ViTs) have recently shown strong performance in dermoscopic image analysis; however, their effe...

  • Article
  • Open Access
452 Views
22 Pages

MoR–Swin: Efficient Vision Transformer Using Mixture of Recursions

  • Yongbao Ai,
  • Tianxiang Gao,
  • Zhipeng Lin,
  • Longqi Yang and
  • Qingyu Chang

12 August 2026

Vision Transformers, especially Swin Transformer, have become default backbones for various vision tasks but suffer from high memory consumption and training costs. This letter proposes MoR–Swin, a novel architecture that integrates Mixture of...

(This article belongs to the Special Issue Computer Vision and Deep Learning: Trends and Applications (3rd Edition))
  • Article
  • Open Access
16 Citations
3,858 Views
21 Pages

A Research on Emotion Recognition of the Elderly Based on Transformer and Physiological Signals

  • Guohong Feng,
  • Hongen Wang,
  • Mengdi Wang,
  • Xiao Zheng and
  • Runze Zhang

Aiming at problems such as the difficulty of recognizing emotions in the elderly and the inability of traditional machine-learning models to effectively capture the nonlinear relationship between physiological signal data, a Recursive Map (RM) combin...

(This article belongs to the Special Issue Applied AI in Emotion Recognition)
  • Article
  • Open Access
9 Citations
2,910 Views
16 Pages

A Recursive Prediction-Based Feature Enhancement for Small Object Detection

  • Xiang Xiao,
  • Xiaorong Xue,
  • Zhiyuan Zhao and
  • Yisheng Fan

14 June 2024

Transformer-based methodologies in object detection have recently piqued considerable interest and have produced impressive results. DETR, an end-to-end object detection framework, ingeniously integrates the Transformer architecture, traditionally us...

(This article belongs to the Section Sensor Networks)
  • Article
  • Open Access
1,636 Views
35 Pages

Visual Mamba-Inspired Directionally Gated State-Space Backtracking for Chemical Gas Source Localization

  • Jooyoung Park,
  • Daehong Min,
  • Sungjin Cho,
  • Donghee Kang and
  • Hyunwoo Nam

10 October 2025

Rapidly pinpointing the origin of accidental chemical gas releases is essential for effective response. Prior vision pipelines—such as 3D CNNs, CNN–LSTMs, and Transformer-based ViViT models—can improve accuracy but often scale poorl...

  • Article
  • Open Access
32 Citations
4,742 Views
12 Pages

30 November 2022

The technologies and models based on machine vision are widely used for early wildfire detection. Due to the broadness of wild scene and the occlusion of the vegetation, smoke is more easily detected than flame. However, the shapes of the smoke blown...

(This article belongs to the Special Issue Forest Fires Prediction and Detection)
  • Article
  • Open Access
879 Views
16 Pages

5 January 2026

Fin-de-siècle decadence—marked by symbolism, dandyism, aesthetic withdrawal, and defiance of bourgeois norms—has long been reimagined beyond its original European contours. Vladimir Nabokov’s Ada or Ardor: A Family Chronicle...

(This article belongs to the Special Issue The Use and Misuse of Fin-De-Siècle Decadence and Its Imagination)
  • Article
  • Open Access
6 Citations
1,325 Views
36 Pages

24 March 2026

Emerging technologies are increasingly positioned as key enablers of sustainable management; however, existing research largely examines digital transformation and sustainability as parallel rather than integrated processes, particularly within natio...

(This article belongs to the Section Sustainable Management)
  • Article
  • Open Access
2 Citations
4,416 Views
17 Pages

24 November 2022

Image super resolution (SR) is an important image processing technique in computer vision to improve the resolution of images and videos. In recent years, deep convolutional neural network (CNN) has made significant progress in the field of image SR;...

(This article belongs to the Section Sensing and Imaging)