Learning Common Semantics via Optimal Transport for Contrastive Multi-View Clustering [0.03%]
基于最优传输的对比多视图聚类的常识学习方法
Qian Zhang,Lin Zhang,Ran Song et al.
Qian Zhang et al.
Multi-view clustering aims to learn discriminative representations from multi-view data. Although existing methods show impressive performance by leveraging contrastive learning to tackle the representation gap between every two views, they...
Semantic-Aware Message Broadcasting for Efficient Unsupervised Domain Adaptation [0.03%]
一种高效的无监督领域自适应语义感知消息广播方法
Xin Li,Cuiling Lan,Guoqiang Wei et al.
Xin Li et al.
Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distribution data). To mitigat...
Unfolded Proximal Neural Networks for Robust Image Gaussian Denoising [0.03%]
展开的 proximal 神经网络以具备鲁棒性的图像高斯去噪为目标
Hoang Trieu Vy Le,Audrey Repetti,Nelly Pustelnik
Hoang Trieu Vy Le
A common approach to solve inverse imaging problems relies on finding a maximum a posteriori (MAP) estimate of the original unknown image, by solving a minimization problem. In this context, iterative proximal algorithms are widely used, en...
Graph Embedding Interclass Relation-Aware Adaptive Network for Cross-Scene Classification of Multisource Remote Sensing Data [0.03%]
图嵌入异类关系自适应网络的多源遥感数据跨场景分类方法
Teng Yang,Song Xiao,Jiahui Qu et al.
Teng Yang et al.
The unsupervised domain adaptation (UDA) based cross-scene remote sensing image classification has recently become an appealing research topic, since it is a valid solution to unsupervised scene classification by exploiting well-labeled dat...
Graph-DETR4D: Spatio-Temporal Graph Modeling for Multi-View 3D Object Detection [0.03%]
图 DETR4D：面向多视图 3D 检测的时空图建模
Zehui Chen,Zheng Chen,Zhenyu Li et al.
Zehui Chen et al.
Multi-View 3D object detection (MV3D) has made tremendous progress by leveraging multiple perspective features through surrounding cameras. Despite demonstrating promising prospects in various applications, accurately detecting objects thro...
Inspector for Face Forgery Detection: Defending Against Adversarial Attacks From Coarse to Fine [0.03%]
从粗到细防御人脸伪造：对抗攻击的检测框架
Ruiyang Xia,Dawei Zhou,Decheng Liu et al.
Ruiyang Xia et al.
The emergence of face forgery has raised global concerns on social security, thereby facilitating the research on automatic forgery detection. Although current forgery detectors have demonstrated promising performance in determining authent...
Xuan Wang,Zhong Ji,Yunlong Yu et al.
Xuan Wang et al.
Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning new knowledge from limited training examples without forgetting previous knowledge. However, we observe that existing methods face a challenge known as supervision c...
Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective [0.03%]
顾此失彼：一种超分辨率多目标优化方法的观点
Lingchen Sun,Jie Liang,Shuaizheng Liu et al.
Lingchen Sun et al.
High perceptual quality and low distortion degree are two important goals in image restoration tasks such as super-resolution (SR). Most of the existing SR methods aim to achieve these goals by minimizing the corresponding yet conflicting l...
SelfGCN: Graph Convolution Network With Self-Attention for Skeleton-Based Action Recognition [0.03%]
一种基于自注意力的人体动作识别图卷积网络模型_selfgcn
Zhize Wu,Pengpeng Sun,Xin Chen et al.
Zhize Wu et al.
Graph Convolutional Networks (GCNs) are widely used for skeleton-based action recognition and achieved remarkable performance. Due to the locality of graph convolution, GCNs can only utilize short-range node dependencies but fail to model l...
Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations [0.03%]
自适应盲超分辨率网络用于空间特异和空间非特异退化
Weilei Wen,Chunle Guo,Wenqi Ren et al.
Weilei Wen et al.
Prior methodologies have disregarded the diversities among distinct degradation types during image reconstruction, employing a uniform network model to handle multiple deteriorations. Nevertheless, we discover that prevalent degradation mod...