Computational color constancy refers to the estimation of the scene illumination and makes the perceived color relatively stable under varying illumination. In the past few years, deep Convolutional Neural Networks (CNNs) have delivered superior performance in illuminant estimation. Several representative methods formulate it as a multi-label prediction problem by learning the local appearance of image patches using CNNs. However, these approaches inevitably make incorrect estimations for the ambiguous patches affected by their neighborhood contexts. Inaccurate local estimates are likely to bring in degraded performance when combining into a global prediction. To address the above issues, we propose a contextual deep network for patch-based illuminant estimation equipped with refinement. First, the contextual net with a center-surround architecture extracts local contextual features from image patches, and generates initial illuminant estimates and the corresponding color corrected patches. The patches are sampled based on the observation that pixels with large color differences describe the illumination well. Then, the refinement net integrates the input patches with the corrected patches in conjunction with the use of intermediate features to improve the performance. To train such a network with numerous parameters, we propose a stage-wise training strategy, in which the features and the predicted illuminant from previous stages are provided to the next learning stage with more finer estimates recovered. Experiments show that our approach obtains competitive performance on two illuminant estimation benchmarks.
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation
Northeastern University(东北大学);College of Sciences, Northeastern University(东北大学理学院);Key Laboratory of Differential Equations and Their Applications, Northeastern University(东北大学微分方程及应用重点实验室);Liaoning Provincial Department of Education(辽宁省教育厅);King’s College London(伦敦国王学院);Shenyang sport University(沈阳体育学院)
Robust Low-light Scene Restoration via Illumination Transition
The Hong Kong University of Science and Technology(香港科学与技术大学);The Hong Kong Polytechnic University(香港理工大学);Nanjing University of Posts and Telecommunications(南京邮电大学);University of Surrey(萨里大学)
Dual High-Order Total Variation Model for Underwater Image Restoration
College of Computer Science and Technology, Qingdao University(青岛大学计算机科学与技术学院);Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, the School of Automation and Electrical Engineering, University of Science and Technology Beijing(北京科技大学自动化与电气工程学院 工业过程知识自动化教育部重点实验室)
A General Framework for Generative Self-supervised Learning in Non-invasive Estimation of Physiological Parameters Using Photoplethysmography
School of Computer Science and Engineering(计算机科学与工程学院);Changchun University of Technology(长春理工大学);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education(教育部符号计算与知识工程重点实验室);Jilin University(吉林大学);Smart Health Joint Innovation Laboratory for the New Generation of AI(新一代人工智能智能健康联合创新实验室)
Human Pose Estimation with Spatial Contextual Information
Baidu Research, Baidu Inc.(百度研究部,百度公司);Hong Kong University of Science and Technology(香港科技大学);YouTu Lab, Tencent(优图实验室,腾讯);The Chinese University of Hong Kong(香港中文大学);University of Kentucky(肯塔基大学)
SPyCer: Semi-Supervised Physics-Guided Contextual Attention for Near-Surface Air Temperature Estimation from Satellite Imagery
INSA CVL, Université d’Orléans, PRISME UR 4229(INSA CVL,奥尔良大学,PRISME UR 4229);Université d’Orléans, INSA CVL, PRISME UR 4229(奥尔良大学,INSA CVL,PRISME UR 4229);Université d’Orléans, CEDETE, UR 1210(奥尔良大学,CEDETE,UR 1210)
Human Pose Regression by Combining Indirect Part Detection and Contextual Information
在本文中,我们提出了一种端到端的可训练回归方法,用于从静止图像中估计人体姿态。我们使用建议的Soft-argmax函数将特征映射直接转换为关节坐标,从而形成完全可微的框架。我们的方法能够间接地学习热图表示,而无需额外的人工地面真实生成步骤。因此,可以以无缝的方式将上下文信息包括到姿态预测中。我们在两个非常具有挑战性的数据集上评估了我们的方法,即Leeds Sports Poses(LSP)和MPII Human Pose数据集,在所有现有的回归方法中达到了最佳性能,并且与最先进的基于检测的方法具有可比性。
DCVC-MV: Deep Contextual Multiview Video Compression with Efficient Inter-View Prediction
Department of Computer Science, City University of Hong Kong(城市大学计算机科学系);Faculty of Electrical Engineering and Computer Science, Ningbo University(宁波大学电子工程与计算机科学学院)
MGCA-Net: Multi-Graph Contextual Attention Network for Two-View Correspondence Learning
College of Cyber Security, Jinan University, Guangzhou, China(广州大学网络安全学院);Chongqing Key Laboratory of Image Cognition, College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China(重庆邮电大学计算机科学与技术学院);Peng Cheng Laboratory, Shenzhen, China(鹏城实验室);Department of Computer Science, City University of Hong Kong, Hong Kong, China(香港城市大学计算机科学系)