Ausgabe 3/2024
Inhalt (24 Artikel)
Adversarial robustness improvement for deep neural networks
Charis Eleftheriadis, Andreas Symeonidis, Panagiotis Katsaros
Temporal teacher with masked transformers for semi-supervised action proposal generation
Selen Pehlivan, Jorma Laaksonen
An image quality assessment method based on edge extraction and singular value for blurriness
Lei Zhou, Chuanlin Liu, Amit Yadav, Sami Azam, Asif Karim
Point cloud registration with quantile assignment
Ecenur Oğuz, Yalım Doğan, Uğur Güdükbay, Oya Karaşan, Mustafa Pınar
Hyperspectral image dynamic range reconstruction using deep neural network-based denoising methods
Loran Cheplanov, Shai Avidan, David J. Bonfil, Iftach Klapp
AFMCT: adaptive fusion module based on cross-modal transformer block for 3D object detection
Bingli Zhang, Yixin Wang, Chengbiao Zhang, Junzhao Jiang, Zehao Pan, Jin Cheng, Yangyang Zhang, Xinyu Wang, Chenglei Yang, Yanhui Wang
Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark
David Bojanić, Kristijan Bartol, Josep Forest, Tomislav Petković, Tomislav Pribanić
Kernel based local matching network for video object segmentation
Guoqiang Wang, Lan Li, Min Zhu, Rui Zhao, Xiang Zhang
Ssman: self-supervised masked adaptive network for 3D human pose estimation
Yu Shi, Tianyi Yue, Hu Zhao, Guoping He, Keyan Ren
YOLOMH: you only look once for multi-task driving perception with high efficiency
Liu Fang, Sun Bowen, Miao Jianxi, Su Weixing
Multi-person 3D pose estimation from unlabelled data
Daniel Rodriguez-Criado, Pilar Bachiller-Burgos, George Vogiatzis, Luis J. Manso
Keyframe-based RGB-D dense visual SLAM fused semantic cues in dynamic scenes
Wugen Zhou, Xiaodong Peng, Yun Li, Mingrui Fan, Bo Liu
Tensor-guided learning for image denoising using anisotropic PDEs
Fakhr-eddine Limami, Aissam Hadri, Lekbir Afraites, Amine Laghrib
The improvement of ground truth annotation in public datasets for human detection
Sotheany Nou, Joong-Sun Lee, Nagaaki Ohyama, Takashi Obi
Lunar ground segmentation using a modified U-net neural network
Georgios Petrakis, Panagiotis Partsinevelos
DisRot: boosting the generalization capability of few-shot learning via knowledge distillation and self-supervised learning
Chenyu Ma, Jinfang Jia, Jianqiang Huang, Li Wu, Xiaoying Wang
AP-TransNet: a polarized transformer based aerial human action recognition framework
Chhavi Dhiman, Anunay Varshney, Ved Vyapak
BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking
Vukasin D. Stanojevic, Branimir T. Todorovic
PTDS CenterTrack: pedestrian tracking in dense scenes with re-identification and feature enhancement
Jiazheng Wen, Huanyu Liu, Junbao Li
PSRUNet: a recurrent neural network for spatiotemporal sequence forecasting based on parallel simple recurrent unit
Wei Tian, Fan Luo, Kailing Shen
ET-PointPillars: improved PointPillars for 3D object detection based on optimized voxel downsampling
Yiyi Liu, Zhengyi Yang, JianLin Tong, Jiajia Yang, Jiongcheng Peng, Lihang Zhang, Wangxin Cheng
Study on defect detection of metal castings based on supervised enhancement and attention distillation
Haixia Pan, Han Zhao, Xingyun Wei, Dongdong Zhang, Biao Dong, Jiahua Lan
OmniGlasses: an optical aid for stereo vision CNNs to enable omnidirectional image processing
Julian B. Seuffert, Ana C. Perez Grassi, Hamza Ahmed, Roman Seidel, Gangolf Hirtz