CV: 涵盖cs.CV领域的最新文章[1] Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction链接：http://arxiv.org/abs/1910.08041v1备注：CoRL 2019作者：Ajay Jain;Sergio Casas;Renjie Liao;Yuwen Xiong;Song Feng;Sean Segal;Raquel Urtasun摘要：Self-driving vehicles plan around both static and dynamic objects, applying predictive models of behavior to estimate future locations of the objects in the environment.
[2] Go with the Flow: Perception-refined Physics Simulation链接：http://arxiv.org/abs/1910.07861v1备注：作者：Tom F. H. Runia;Kirill Gavrilyuk;Cees G. M. Snoek;Arnold W. M. Smeulders摘要：For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior.
[3] Conditional Driving from Natural Language Instructions链接：http://arxiv.org/abs/1910.07615v1备注：Accepted by the 3rd Conference on Robot Learning, Osaka, Japan (CoRL  2019)作者：Junha Roh;Chris Paxton;Andrzej Pronobis;Ali Farhadi;Dieter Fox摘要：Widespread adoption of self-driving cars will depend not only on their safety but largely on their ability to interact with human users.
[4] Context-Aware Saliency Detection for Image Retargeting Using  Convolutional Neural Networks链接：http://arxiv.org/abs/1910.08071v1备注：20 pages, 19 figures作者：Mahdi Ahmadi;Nader Karimi;Shadrokh Samavi摘要：Image retargeting is the task of making images capable of being displayed on screens with different sizes.
[5] Meta-learning for fast classifier adaptation to new users of Signature  Verification systems链接：http://arxiv.org/abs/1910.08060v1备注：Accepted for the IEEE Transactions on Information Forensics and  Security作者：Luiz G. Hafemann;Robert Sabourin;Luiz S. Oliveira摘要：Offline Handwritten Signature verification presents a challenging Pattern Recognition problem, where only knowledge of the positive class is available for training. While classifiers have access to a few genuine signatures for training, during generalization they also need to discriminate forgeries.
[6] Video Person Re-Identification using Learned Clip Similarity Aggregation链接：http://arxiv.org/abs/1910.08055v1备注：作者：Neeraj Matiyali;Gaurav Sharma摘要：We address the challenging task of video-based person re-identification. Recent works have shown that splitting the video sequences into clips and then aggregating clip based similarity is appropriate for the task.
[7] Convolutional Character Networks链接：http://arxiv.org/abs/1910.07954v1备注：To appear in ICCV 2019作者：Linjie Xing;Zhi Tian;Weilin Huang;Matthew R. Scott摘要：Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage framework by involving ROI pooling, which can degrade the performance on recognition task.
[8] Can I teach a robot to replicate a line art链接：http://arxiv.org/abs/1910.07860v1备注：9 pages, Accepted for the 2020 Winter Conference on Applications of  Computer Vision (WACV '20); Supplementary Video: https://youtu.be/nMt5Dw04XhY作者：Raghav Brahmadesam Venkataramaiyer;Subham Kumar;Vinay P. Namboodiri摘要：Line art is arguably one of the fundamental and versatile modes of expression. We propose a pipeline for a robot to look at a grayscale line art and redraw it.
[9] NAMF: A Non-local Adaptive Mean Filter for Salt-and-Pepper Noise Removal链接：http://arxiv.org/abs/1910.07787v1备注：作者：Houwang Zhang;Chong Wu;Hanying Zheng;Le Zhang摘要：In this paper, a non-local adaptive mean filter (NAMF) is proposed, which can eliminate all levels of salt-and-pepper (SAP) noise. NAMF can be divided into two stages: (1) SAP noise detection; (2) SAP noise elimination.
[10] Detecting Urban Changes with Recurrent Neural Networks from  Multitemporal Sentinel-2 Data链接：http://arxiv.org/abs/1910.07778v1备注：4 pages, IGARSS2019作者：Maria Papadomanolaki;Sagar Verma;Maria Vakalopoulou;Siddharth Gupta;Konstantinos Karantzalos摘要：\begin{abstract} The advent of multitemporal high resolution data, like the Copernicus Sentinel-2, has enhanced significantly the potential of monitoring the earth's surface and environmental dynamics.
[11] On the Reliability of Cancelable Biometrics: Revisit the Irreversibility链接：http://arxiv.org/abs/1910.07770v1备注：Submit to PR作者：Xingbo Dong;Zhe Jin;Andrew Beng Jin Teoh;Massimo Tistarelli;KokSheik Wong摘要：Over the years, many biometric template protection schemes, primarily based on the notion of "cancelable biometrics" have been proposed. A cancelable biometric algorithm needs to satisfy four biometric template protection criteria, i.e.
[12] Making Third Person Techniques Recognize First-Person Actions in  Egocentric Videos链接：http://arxiv.org/abs/1910.07766v1备注：5 pages, ICIP2018,  code:https://github.com/sagarverma/ego_action_recognition作者：Sagar Verma;Pravin Nagar;Divam Gupta;Chetan Arora摘要：We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories.
[13] Deep Contextual Attention for Human-Object Interaction Detection链接：http://arxiv.org/abs/1910.07721v1备注：Accepted at ICCV 2019作者：Tiancai Wang;Rao Muhammad Anwer;Muhammad Haris Khan;Fahad Shahbaz Khan;Yanwei Pang;Ling Shao;Jorma Laaksonen摘要：Human-object interaction detection is an important and relatively new class of visual relationship detection tasks, essential for deeper scene understanding. Most existing approaches decompose the problem into object localization and interaction recognition.
[14] Cross Attention Network for Few-shot Classification链接：http://arxiv.org/abs/1910.07677v1备注：12 pages, 4 figures. NeurIPS 2019 (Accepted)作者：Ruibing Hou;Hong Chang;Bingpeng Ma;Shiguang Shan;Xilin Chen摘要：Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples. The unseen classes and low-data problem make few-shot classification very challenging.
[15] RGB-D Individual Segmentation链接：http://arxiv.org/abs/1910.07641v1备注：10 pages, 7 figures作者：Wenqiang Xu;Yanjun Fu;Yuchen Luo;Chang Liu;Cewu Lu摘要：Fine-grained recognition task deals with sub-category classification problem, which is important for real-world applications. In this work, we are particularly interested in the segmentation task on the \emph{finest-grained} level, which is specifically named "individual segmentation".
[16] A Combined Deep Learning-Gradient Boosting Machine Framework for Fluid  Intelligence Prediction链接：http://arxiv.org/abs/1910.07640v1备注：Challenge in Adolescent Brain Cognitive Development Neurocognitive  Prediction作者：Yeeleng S. Vang;Yingxin Cao;Xiaohui Xie摘要：The ABCD Neurocognitive Prediction Challenge is a community driven competition asking competitors to develop algorithms to predict fluid intelligence score from T1-w MRIs. In this work, we propose a deep learning combined with gradient boosting machine framework to solve this task.
[17] Global Saliency: Aggregating Saliency Maps to Assess Dataset Artefact  Bias链接：http://arxiv.org/abs/1910.07604v1备注：Machine Learning for Health (ML4H) Workshop at NeurIPS 2019作者：Jacob Pfau;Albert T. Young;Maria L. Wei;Michael J. Keiser摘要：In high-stakes applications of machine learning models, interpretability methods provide guarantees that models are right for the right reasons.
[18] Instance adaptive adversarial training: Improved accuracy tradeoffs in  neural nets链接：http://arxiv.org/abs/1910.08051v1备注：作者：Yogesh Balaji;Tom Goldstein;Judy Hoffman摘要：Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test set.
[19] Adaptive Curriculum Generation from Demonstrations for Sim-to-Real  Visuomotor Control链接：http://arxiv.org/abs/1910.07972v1备注：作者：Lukas Hermann;Max Argus;Andreas Eitel;Artemij Amiranashvili;Wolfram Burgard;Thomas Brox摘要：We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards.
[20] Self-supervised 3D Shape and Viewpoint Estimation from Single Images for  Robotics链接：http://arxiv.org/abs/1910.07948v1备注：Accepted at the 2019 IEEE/RSJ International Conference on Intelligent  Robots and Systems (IROS). Video at  https://www.youtube.com/watch?v=oQgHG9JdMP4作者：Oier Mees;Maxim Tatarchenko;Thomas Brox;Wolfram Burgard摘要：We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of self-supervision.
[21] A New Three-stage Curriculum Learning Approach to Deep Network Based  Liver Tumor Segmentation链接：http://arxiv.org/abs/1910.07895v1备注：5 pages, 3 figures, 1 table, conference作者：Huiyu Li;Xiabi Liu;Said Boumaraf;Weihua Liu;Xiaopeng Gong;Xiaohong Ma摘要：Automatic segmentation of liver tumors in medical images is crucial for the computer-aided diagnosis and therapy. It is a challenging task, since the tumors are notoriously small against the background voxels.
[22] Introducing Hann windows for reducing edge-effects in patch-based image  segmentation链接：http://arxiv.org/abs/1910.07831v1备注：作者：Nicolas Pielawski;Carolina W?hlby摘要：There is a limitation in the size of an image that can be processed using computationally demanding methods such as e.g. Convolutional Neural Networks (CNNs).
[23] Organ At Risk Segmentation with Multiple Modality链接：http://arxiv.org/abs/1910.07800v1备注：作者：Kuan-Lun Tseng;Winston Hsu;Chun-ting Wu;Ya-Fang Shih;Fan-Yun Sun摘要：With the development of image segmentation in computer vision, biomedical image segmentation have achieved remarkable progress on brain tumor segmentation and Organ At Risk (OAR) segmentation.
[24] Annealed Denoising Score Matching: Learning Energy-Based Models in  High-Dimensional Spaces链接：http://arxiv.org/abs/1910.07762v1备注：作者：Zengyi Li;Yubei Chen;Friedrich T. Sommer摘要：Energy-Based Models (EBMs) outputs unmormalized log-probability values given data samples. Such an estimation is essential in a variety of applications such as sample generation, denoising, sample restoration, outlier detection, Bayesian reasoning, and many more.
[25] A Parametric Perceptual Deficit Modeling and Diagnostics Framework for  Retina Damage using Mixed Reality链接：http://arxiv.org/abs/1910.07688v1备注：作者：Prithul Aniruddha;Nasif Zaman;Alireza Tavakkoli;Stewart Zuckerbrod摘要：Age-related Macular Degeneration (AMD) is a progressive visual impairment affecting millions of individuals. Since there is no current treatment for the disease, the only means of improving the lives of individuals suffering from the disease is via assistive technologies.
[26] CFEA: Collaborative Feature Ensembling Adaptation for Domain Adaptation  in Unsupervised Optic Disc and Cup Segmentation链接：http://arxiv.org/abs/1910.07638v1备注：作者：Peng Liu;Bin Kong;Zhongyu Li;Shaoting Zhang;Ruogu Fang摘要：Recently, deep neural networks have demonstrated comparable and even better performance with board-certified ophthalmologists in well-annotated datasets.
[27] Optimal Transport Based Generative Autoencoders链接：http://arxiv.org/abs/1910.07636v1备注：15 pages作者：Oliver Zhang;Ruei-Sung Lin;Yuchuan Gou摘要：The field of deep generative modeling is dominated by generative adversarial networks (GANs). However, the training of GANs often lacks stability, fails to converge, and suffers from model collapse.