BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation [0.03%]
BinsFormer：单目深度估计中自适应柱状图的再探究
Zhenyu Li,Xuyang Wang,Xianming Liu et al.
Zhenyu Li et al.
Monocular depth estimation (MDE) is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth i...
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning [0.03%]
超越特征对齐的泛化能力：概念激活引导的对比学习
Yibing Liu,Chris Xing Tian,Haoliang Li et al.
Yibing Liu et al.
Learning invariant representations via contrastive learning has seen state-of-the-art performance in domain generalization (DG). Despite such success, in this paper, we find that its core learning strategy - feature alignment - could heavil...
Zhifeng Xie,Rui Qiu,Sen Wang et al.
Zhifeng Xie et al.
Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled night image datasets, unsupervised domain adaptation (UDA)...
Causality-Enhanced Multiple Instance Learning With Graph Convolutional Networks for Parkinsonian Freezing-of-Gait Assessment [0.03%]
基于因果图卷积网络的帕金森病冻结步态评估的多重实例学习方法
Rui Guo,Zheng Xie,Chencheng Zhang et al.
Rui Guo et al.
Freezing of gait (FoG) is a common disabling symptom of Parkinson's disease (PD). It is clinically characterized by sudden and transient walking interruptions for specific human body parts, and it presents the localization in time and space...
Incrementally Adapting Pretrained Model Using Network Prior for Multi-Focus Image Fusion [0.03%]
基于网络先验的多焦点图像融合的增量式预训练模型自适应方法
Xingyu Hu,Junjun Jiang,Chenyang Wang et al.
Xingyu Hu et al.
Multi-focus image fusion can fuse the clear parts of two or more source images captured at the same scene with different focal lengths into an all-in-focus image. On the one hand, previous supervised learning-based multi-focus image fusion ...
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction [0.03%]
基于多条件潜在扩散模型的场景感知神经人体运动预测方法
Xuehao Gao,Yang Yang,Yang Wu et al.
Xuehao Gao et al.
Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one's intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven...
L₀ Gradient-Regularization and Scale Space Representation Model for Cartoon and Texture Decomposition [0.03%]
基于L0梯度正则化和尺度空间表示的图像分解模型
Huan Pan,You-Wei Wen,Ya Huang
Huan Pan
In this paper, we consider decomposing an image into its cartoon and texture components. Traditional methods, which mainly rely on the gradient amplitude of images to distinguish between these components, often show limitations in decomposi...
Semi-Supervised Learning With Heterogeneous Distribution Consistency for Visible Infrared Person Re-Identification [0.03%]
基于异质分布一致性的半监督学习可见光红外人再识别方法
Ziyu Wei,Xi Yang,Nannan Wang et al.
Ziyu Wei et al.
Visible infrared person re-identification (VI-ReID) exposes considerable challenges because of the modality gaps between the person images captured by daytime visible cameras and nighttime infrared cameras. Several fully-supervised VI-ReID ...
A Single-Frame Deflectometry Method for Online Inspection of Light-Transmitting Components [0.03%]
一种用于透光零件在线检测的单帧偏折法
Ning Yan,Dongxue Wang,Lei Liu et al.
Ning Yan et al.
Transparent materials are widely used in industrial applications, such as construction, transportation, and optics. However, the complex optical properties of these materials make it difficult to achieve precise surface form measurements, e...
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency [0.03%]
基于跨对象一致性的复杂遥感场景半监督分类方法
Qiang Liu,Jun Yue,Yang Kuang et al.
Qiang Liu et al.
Semi-supervised learning (SSL), which aims to learn with limited labeled data and massive amounts of unlabeled data, offers a promising approach to exploit the massive amounts of satellite Earth observation images. The fundamental concept u...