IEEE

Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition

Abstract: Pedestrian attribute recognition (PAR) seeks to predict multiple semantic attributes associated with a specific pedestrian. There are two types of approaches for PAR: unimodal framework and ...
IEEE

Multimodal Contrastive Learning for Cybersickness Recognition Using Brain Connectivity Graph Representation

Abstract: Cybersickness significantly impairs user comfort and immersion in virtual reality (VR). Effective identification of cybersickness leveraging physiological, visual, and motion data is a ...
IEEE

Neonatal Pain Speech Emotion Recognition Based on Multiscale Multilevel MAE Network

Abstract: Perception of neonatal pain is a critical indicator for early-life health assessment. However, in real-world clinical scenarios, it faces challenges such as poor objectivity and limited ...
IEEE

High-Performance CNN-Based Facial Recognition on the Yale Face Database

Abstract: Facial identification and detection have significantly risen due to deep learning techniques, especially Convolutional Neural Networks (CNNs), which perform better than traditional methods ...
IEEE

Special Convolution and Mask R-CNN: A New Method for Text Recognition on Cultural Relics

Abstract: This paper explores the use of artificial intelligence technology to restore and recognize blurred text on cultural relics. Traditional OCR technology has limitations in dealing with ...
IEEE

Performance Analysis of CNN-Based Spectrogram with Multiple Audio Feature Types for English Digit Recognition

Abstract: Audio feature selection and neural network architecture play crucial roles in speech recognition performance. This paper presents a comparative analysis of Artificial Neural Networks (ANNs) ...
IEEE

Comparative Study of CNN Models for Human Action Recognition in Detection Tasks

Abstract: Aiming at the performance optimization of convolutional neural networks in human action recognition tasks, this study constructs a system evaluation framework containing eight typical ...
IEEE

Arcface-Integrated Max Feature Map CNN for Robust Face Recognition

Abstract: Face recognition remains challenging, especially with small and imbalanced datasets that reduce feature discriminability and limit generalization. This study investigates Light Convolutional ...
IEEE

Recognition of Stroke Level Based on EEG Signal Using Multi-networks of CNN-Transformer

Abstract: Stroke is a major cause of long-term neurological impairment, and continuous monitoring of post-stroke patients is essential for rehabilitation and relapse prevention. Electroencephalogram ...
IEEE

CNN-Transformer-Bi-LSTM: A Hybrid Deep Learning Framework for Wearable Sensor-Based Human Activity Recognition

Abstract: Human activity recognition (HAR) focuses on identifying and classifying human activities based on data collected from various sources. Its importance lies in its wide range of applications, ...
IEEE

Double Nonconvex Tensor Robust Kernel Principal Component Analysis and Its Visual Applications

Abstract: Tensor robust principal component analysis (TRPCA), as a popular linear low-rank method, has been widely applied to various visual tasks. The mathematical process of the low-rank prior is ...
IEEE

A Transparent Baseline for LoRa Device Fingerprinting with CNN

Abstract: Device authentication based on radio frequency fingerprinting (RFF) offers a non-cryptographic alternative for identifying LoRa devices in IoT deployments, but research in this area is often ...