Search Results - "2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)"

An Efficient Convolutional Multi-Scale Vision Transformer for Image Classification by Zhang, Ji, Chen, Zhihao, Ge, Yiyuan, Yu, Mingxin

“…This paper introduces an innovative and efficient multi-scale Vision Transformer (ViT) for the task of image classification. The proposed model leverages the…”
Get full text

Multi-branch Person Re-identification Net by Chen, Zhihao, Ge, Yiyuan, Zhang, Ji, Gao, Xiang

“…Person ReID is a complex and important problem within the domain of computer vision. Its objective is to identify and match individuals in video sequences,…”
Get full text

End-to-End Person Search Based on Content Awareness by Ge, Yiyuan, Zhang, Ji, Chen, Zhihao, Li, Bi

“…Within the domain of computer vision, person search stands out as a crucial and intricate undertaking. With the growth of urban population and the popularity…”
Get full text

Fast Super-Resolution Network via Dynamic Path Selection by Jia, Longfei, Hu, Yuguo, Tian, Xianlong, Luo, Wenwei

“…In the context of edge computing environments, where the storage space and computational resources are constrained, complex super-resolution network models…”
Get full text

Refined Feature Fusion-Based Transformer Network for Hyperspectral and LiDAR classification by Shen, Xinxin, Zhu, Hongyu, Meng, Chao

“…Multimodal remote sensing images describe the same surface scene from different viewpoints, and can gain more reliable information about the earth's surface…”
Get full text

Novel View Synthesis from a Single RGBD Image for Indoor Scenes by Hetang, Congrui, Wang, Yuping

“…In this paper, we propose an approach for synthesizing novel view images from a single RGBD (Red Green Blue-Depth) input. Novel view synthesis (NVS) is an…”
Get full text

Imbalance Label Enhancement with Adaptive Neighbors by Qian, Wei, Li, Weiwei

“…Label distribution learning (LDL) is gaining popularity due to its more generalized capacity to deal with label ambiguity. The cost of collecting label…”
Get full text

Video Behavior Recognition Model Based on 3D Reprameterized Convolution by Liu, Ping, Xie, Sheng, Lin, Chaofu, Wu, Hao

“…In addressing the challenge posed by the extensive parameters of 3D convolutional modules, this paper extends the 2D reparameterization method to propose a 3D…”
Get full text

Masked Face Recognition Method with Dual-branch Attention by Zhao, Jiangbin, Wang, Wei

“…Air pollution and the presence of toxic gases in daily life pose a significant health concern, leading people to wear masks for protection. However, wearing…”
Get full text

A Preprocessing Method for Fragment Perforation Image Detection by Lu, Guangzhao, Sun, Yong, Huang, Dan, Zhao, Jinqing

“…The perforation data left by the fragments generated by the explosion of ammunition warheads on the surrounding metal plates can reflect the dispersion…”
Get full text

A solar irradiance prediction method based on signal decomposition and Informer by Xu, Zhiwu

“…The historical data of solar irradiance are characterized by volatility and instability. These characteristics make it difficult to obtain satisfactory results…”
Get full text

A multi-view stable feature extraction network for SAR target recognition by Xiao, Ziyi, Zhang, Gong, Dai, Qijun, Wang, Zijun

“…Since the viewing angle sensitivity of Synthetic Aperture Radar (SAR) image, targets' shape changes dramatically in different viewing angle, the accuracy of…”
Get full text

LSTM Model and Data Segmentation Collaboration A Deep Learning Strategy for Traffic Flow Anomaly Detection Using SUMO Simulated Data by Hu, Lai

“…To address the escalating challenge of traffic congestion and the associated difficulties in obtaining specific congestion data sets, this paper explores the…”
Get full text

Spiking-Timing-Dependent Plasticity Convolutional Spiking Neural Network for Efficient Radar-Based Gesture Recognition by Wu, Yifan, Wu, Li, Xiao, Zelong, Hu, Taiyang

“…An innovative architecture, termed Spike-Timing-Dependent Plasticity Convolutional Spiking Neural Network (STDP-CSNN), is proposed for efficient radar-based…”
Get full text

Training Spiking Neural Networks Using Randomness by Lin, Hao

“…Artificial neural networks have demonstrated remarkable performance across many fields. However, their high training cost has led researchers to seek ways to…”
Get full text

FSPN: Feature Selection Pyramid Network for Tiny Person Detection by Hu, Jiangwen, Dong, Fangfang

“…Object detection is an important research direction in the field of computer vision, which aims to classify and locate objects in the input image. Among them,…”
Get full text

Panoramic image depth estimation based on deformable convolution and attention mechanism by Shao, Fangfang, Xu, Chao, Han, Cheng, Wang, Shiwen

“…Currently, mainstream panoramic depth estimation methods primarily focus on correcting distortion effects. For Convolutional Neural Networks (CNN) based on…”
Get full text

Application of Improved Canny Algorithm in Image Edge Detection of Transmission Lines by Zhang, Gangzi, Zhang, Guowei, Lu, Qiuhong, Bo, Yunlong, Zhou, Xinrui

“…Aiming at the incoherence and inaccuracy of traditional canny algorithm for transmission line image edge detection, an improved Canny algorithm is proposed for…”
Get full text

Defect detection of photovoltaic modules based on improved SSD algorithm by Kong, Xiangyu, Xu, Wanxuan, Xu, Bohao, Jin, Hui, Zhan, Peihong

“…Automated inspection of unmanned aerial vehicles (UAVs) offers an effective solution to address the operational and maintenance requirements of large-scale…”
Get full text

A Review of Research on Generalization Error Analysis of Deep Learning Models by Zhang, Zimu, Zhang, Xiujian

“…Generalization error is used to quantify the predictive ability of models on unseen datasets, which are obtained from learning based on training datasets. The…”
Get full text