Machine Vision and Applications

Pakistan sign language recognition: leveraging deep learning models with limited dataset

Hafiz Muhammad Hamza, Aamir Wali

A high-level feature channel attention UNet network for cholangiocarcinoma segmentation from microscopy hyperspectral images

Hongmin Gao, Mengran Yang, Xueying Cao, Qin Liu, Peipei Xu

When dual contrastive learning meets disentangled features for unpaired image deraining

Tianming Wang, Kaige Wang, Qing Li

Occlusion recovery face recognition based on information reconstruction

Huanjie He, Jiuzhen Liang, Zhenjie Hou, Hao Liu, Xinwen Zhou

Traffic sign detection and recognition under low illumination

Jiana Yao, Bingqiang Huang, Song Yang, Xinjian Xiang, Zhigang Lu

MFEMANet: an effective disaster image classification approach for practical risk assessment

Payal Bhadra, Avijit Balabantaray, Ajit Kumar Pasayat

A robust vehicle tracking in low-altitude UAV videos

Bahri Maraş, Nafiz Arica, Ayşın Ertüzün

PerSnake: a real-time pedestrian instance segmentation network using contour representation

Zhiyang Guo, Xincan Wang, Zhihua Zhang, Yingping Huang, Xueyin Ma

Probabilistic multi-modal depth estimation based on camera–LiDAR sensor fusion

Johan S. Obando-Ceron, Victor Romero-Cano, Sildomar Monteiro

FFA-Net: fast feature aggregation network for 3D point cloud segmentation

Ruting Cheng, Hui Zeng, Baoqing Zhang, Xuan Wang, Tianmeng Zhao

Variable exponent diffusion for image detexturing

Pierre-Alain Fayolle, Alexander G. Belyaev

Unsupervised single-shot depth estimation using perceptual reconstruction

Christoph Angermann, Matthias Schwab, Markus Haltmeier, Christian Laubichler, Steinbjörn Jónsson

FLAVR: flow-free architecture for fast video frame interpolation

Tarun Kalluri, Deepak Pathak, Manmohan Chandraker, Du Tran

Residual shuffle attention network for image super-resolution

Xuanyi Li, Zhuhong Shao, Bicao Li, Yuanyuan Shang, Jiasong Wu, Yuping Duan

AFC-Net: adjacent feature complementary for crowded pedestrian detection

Jing Wang, Cailing Zhao, Zhiqiang Liu, Zhanqiang Huo

RGB-LiDAR fusion for accurate 2D and 3D object detection

Morteza Mousa-Pasandi, Tianran Liu, Yahya Massoud, Robert Laganière

A dual-path U-Net for pulmonary vessel segmentation method based on lightweight 3D attention

Rencheng Wu, Yu Xin, Yihong Dong, Jiangbo Qian

Editor’s Note: Special Issue from Winter Conference on Applications of Computer Vision - WACV 2023

Instance-dimension dual contrastive learning of visual representations

Qingrui Liu, Liantao Wang, Qinxu Wang, Jinxia Zhang

Highly transparent material classification using the refractive index, reflectivity, and transmissivity features from an imaging model of a time-of-flight camera

Shinan Lang, Fangyi Chen, Yiheng Cai

Modeling driving task-relevant attention for intelligent vehicles using triplet ranking

Jayani Withanawasam, Shunsuke Kamijo

Representing dynamic textures based on polarized gradient features

Thanh Tuan Nguyen, Thanh Phuong Nguyen, Frédéric Bouchara

Multi-distribution fitting for multi-view stereo

Jinguang Chen, Zonghua Yu, Lili Ma, Kaibing Zhang

An automated framework to evaluate soft skills using posture and disfluency detection

Vaibhav Gulati, Srijan Dwivedi, Deepika Kumar, Jatin Wadhwa, Devaansh Dhingra, Jude D. Hemanth