Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow methods, it remains a challenge to accurately estimate large displacements with motion blur. This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images. The locality of convolutional features makes the computed correlations susceptible to various noises. On large displacements with motion blur, noisy correlations could cause severe errors in the estimated flow. To overcome this challenge, we propose a new architecture "CRoss-Attentional Flow Transformer" (CRAFT), aiming to revitalize the correlation volume computation. In CRAFT, a Semantic Smoothing Transformer layer transforms the features of one frame, making them more global and semantically stable. In addition, the dot-product correlations are replaced with transformer Cross-Frame Attention. This layer filters out feature noises through the Query and Key projections, and computes more accurate correlations. On Sintel (Final) and KITTI (foreground) benchmarks, CRAFT has achieved new state-of-the-art performance. Moreover, to test the robustness of different models on large motions, we designed an image shifting attack that shifts input images to generate large artificial motions. Under this attack, CRAFT performs much more robustly than two representative methods, RAFT and GMA. The code of CRAFT is is available at https://github.com/askerlee/craft.
An Improved End-to-End Multi-Target Tracking Method Based on Transformer Self-Attention
Wuhan University（武汉大学）；Wuhan Optics Valley Information Technology Co., Ltd.（武汉光谷信息技术股份有限公司）；Mobile Broadcasting and Information Service Industry Innovation Research Institute (Wuhan) Co., Ltd（移动广播与信息服务产业创新研究院（武汉）有限公司）
Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
Politecnico di Torino（都灵理工大学）；PIC4SeR, Politecnico di Torino Interdepartmental Centre for Service Robotics（都灵理工大学跨部门服务机器人中心 PIC4SeR）；Newcastle University（纽卡斯尔大学）
Multi-label Image Recognition by Recurrently Discovering Attentional Regions
Sun Yat-sen University（中山大学）；SenseTime Group Limited（商汤集团有限公司）；Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education（教育部先进计算工程软件工程研究中心）
Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification
UFRGS（联邦大学里约格兰德杜斯鲁斯）；Institute of Informatics（信息学院）；Federal University of Rio Grande do Sul（里约格兰德杜斯鲁斯联邦大学）；Division of Informatics（信息系）；School of Health Sciences（健康科学学院）；Imaging and Data Science（成像与数据科学）；Faculty of Biology, Medicine and Health（生物医学与健康学院）；University of Manchester（曼彻斯特大学）；Vaughan House, Portsmouth St（波特兰街瓦尔赫恩大楼）
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution
School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；College of Computer Science, Nankai University（南开大学计算机学院）
Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder
Harvard University（哈佛大学）；Singapore Management University（新加坡管理大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；South Australian Health and Medical Research Institute（南澳大利亚健康与医学研究所）；University of Surrey（萨里大学）
DB SwinT: A Dual-Branch Swin Transformer Network for Road Extraction in Optical Remote Sensing Imagery
School of Information Science and Engineering（信息科学与工程学院）；Chongqing Jiaotong University（重庆交通大学）；College of Information Engineering（信息工程学院）；Inner Mongolia University of Technology（内蒙古科技大学）；Inner Mongolia Key Laboratory of Radar Technology and Application（内蒙古雷达技术与应用重点实验室）
Learning Visual Prompts for Guiding the Attention of Vision Transformers
School of Computation, Information and Technology（计算、信息与技术学院）；Technical University of Munich（慕尼黑工业大学）；AI Innovation, Data:Lab Munich（慕尼黑人工智能创新数据实验室）；Volkswagen AG（大众汽车集团）；Department of Engineering Science（工程科学系）；University of Oxford（牛津大学）
Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer
Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Department of Automation, Tsinghua University（清华大学自动化系）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）
PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptation
Westlake Institute for Advanced Studies（西湖研究学院）；Centre for Artificial Intelligence（人工智能中心）；State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)（多模态人工智能系统国家重点实验室）；Institute of Automation（自动化研究所）；Chinese Academy of Sciences (CASIA)（中国科学院）；School of Artificial Intelligence（人工智能学院）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Alibaba Group（阿里巴巴集团）；School of Computer Science（计算机学院）；Engineering, the Faculty of Innovation Engineering, Macau University of Science（工程学院，创新工程 faculty，澳门科学大学）；Microsoft（微软公司）
