Deep Human Parsing with Active Template Regression
Sun Yat-sen University（中山大学）；National University of Singapore（新加坡国立大学）；SYSU-CMU Shunde International Joint Research Institute（中山大学-卡内基梅隆大学顺德国际联合研究院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Xiaodan Liang, Si Liu, Xiaohui Shen, Jianchao Yang, Luoqi Liu, Jian Dong, Liang Lin, Shuicheng Yan
In this work, the human parsing task, namely decomposing a human image into semantic fashion/body regions, is formulated as an Active Template Regression (ATR) problem, where the normalized mask of each fashion/body item is expressed as the linear combination of the learned mask templates, and then morphed to a more precise mask with the active shape parameters, including position, scale and visibility of each semantic region. The mask template coefficients and the active shape parameters together can generate the human parsing results, and are thus called the structure outputs for human parsing. The deep Convolutional Neural Network (CNN) is utilized to build the end-to-end relation between the input human image and the structure outputs for human parsing. More specifically, the structure outputs are predicted by two separate networks. The first CNN network is with max-pooling, and designed to predict the template coefficients for each label mask, while the second CNN network is without max-pooling to preserve sensitivity to label mask position and accurately predict the active shape parameters. For a new image, the structure outputs of the two networks are fused to generate the probability of each label for each pixel, and super-pixel smoothing is finally used to refine the human parsing result. Comprehensive evaluations on a large dataset well demonstrate the significant superiority of the ATR framework over other state-of-the-arts for human parsing. In particular, the F1-score reaches $64.38\%$ by our ATR framework, significantly higher than $44.76\%$ based on the state-of-the-art algorithm.
SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks
Swinburne Vietnam, FPT University（斯威本越南，FPT大学）；Posts and Telecommunications Institute of Technology（邮电技术学院）；Academy of Cryptography Techniques（密码技术学院）；The University of Electro-Communications（电气通信大学）
Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Gettysburg College（盖蒂斯堡学院）；Instituto Politécnico Nacional (IPN)（国立理工学院）；Michigan State University（密歇根州立大学）；HSE University（高等经济学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution
School of Computer Science, Chengdu University of Information Technology（成都信息工程大学计算机科学学院）；Faculty of Mechanical Engineering and Mechanics, Ningbo University（宁波大学机械与力学学院）
University of Tübingen（蒂宾根大学）；Tübingen AI Center（蒂宾根人工智能中心）；Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
