Yu Zheng,Jiwen Lu,Yueqi Duan et al.
Yu Zheng et al.
In this paper, we propose an effective plug-and-play module called structural relation network (SRN) to model structural dependencies in 3D point clouds for feature representation. Existing network architectures such as PointNet++ and RS-CN...
Contrastive Open-Set Active Learning-Based Sample Selection for Image Classification [0.03%]
基于对比开放集主动学习的图像分类样本选择方法
Zizheng Yan,Delian Ruan,Yushuang Wu et al.
Zizheng Yan et al.
In this paper, we address a complex but practical scenario in Active Learning (AL) known as open-set AL, where the unlabeled data consists of both in-distribution (ID) and out-of-distribution (OOD) samples. Standard AL methods will fail in ...
Generating Stylized Features for Single-Source Cross-Dataset Palmprint Recognition With Unseen Target Dataset [0.03%]
具有未知目标数据集的单源跨数据集掌纹识别的 stylize特征生成方法
Huikai Shao,Pengxu Li,Dexing Zhong
Huikai Shao
As a promising topic in palmprint recognition, cross-dataset palmprint recognition is attracting more and more research interests. In this paper, a more difficult yet realistic scenario is studied, i.e., Single-Source Cross-Dataset Palmprin...
Style Consistency Unsupervised Domain Adaptation Medical Image Segmentation [0.03%]
无监督领域适应风格一致性的医学图像分割
Lang Chen,Yun Bian,Jianbin Zeng et al.
Lang Chen et al.
Unsupervised domain adaptation medical image segmentation is aimed to segment unlabeled target domain images with labeled source domain images. However, different medical imaging modalities lead to large domain shift between their images, i...
Reference-Based Multi-Stage Progressive Restoration for Multi-Degraded Images [0.03%]
基于参考的多阶段逐步恢复用于多种退化图像的方法
Yi Zhang,Qixue Yang,Damon M Chandler et al.
Yi Zhang et al.
Image restoration (IR) via deep learning has been vigorously studied in recent years. However, due to the ill-posed nature of the problem, it is challenging to recover the high-quality image details from a single distorted input especially ...
Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection [0.03%]
基于弱监督视频异常检测的提示增强上下文特征学习方法
Yujiang Pu,Xiaoyu Wu,Lulu Yang et al.
Yujiang Pu et al.
Weakly supervised video anomaly detection aims to locate abnormal activities in untrimmed videos without the need for frame-level supervision. Prior work has utilized graph convolution networks or self-attention mechanisms alongside multipl...
M2GCNet: Multi-Modal Graph Convolution Network for Precise Brain Tumor Segmentation Across Multiple MRI Sequences [0.03%]
跨多种MRI序列的精确脑肿瘤分割的多模态图卷积网络(M2GCNet)
Tongxue Zhou
Tongxue Zhou
Accurate segmentation of brain tumors across multiple MRI sequences is essential for diagnosis, treatment planning, and clinical decision-making. In this paper, I propose a cutting-edge framework, named multi-modal graph convolution network...
Bardia Azizian,Ivan V Bajic
Bardia Azizian
Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural Network (DNN) model runs on the edge, and the rest is executed on the cloud. In such applications, the machine vision model does not need the exact v...
Blind Video Quality Prediction by Uncovering Human Video Perceptual Representation [0.03%]
基于人类视频感知表征的盲视质量预测方法研究
Liang Liao,Kangmin Xu,Haoning Wu et al.
Liang Liao et al.
Blind video quality assessment (VQA) has become an increasingly demanding problem in automatically assessing the quality of ever-growing in-the-wild videos. Although efforts have been made to measure temporal distortions, the core to distin...
Balanced Destruction-Reconstruction Dynamics for Memory-Replay Class Incremental Learning [0.03%]
兼顾破坏与重构的动态机制在增量学习中的应用
Yuhang Zhou,Jiangchao Yao,Feng Hong et al.
Yuhang Zhou et al.
Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e., cat...