2018 15th Conference on Computer and Robot Vision (CRV)最新文献_第5页

Convolutional Neural Networks Regularized by Correlated Noise 相关噪声正则化卷积神经网络

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-04-03 DOI: 10.1109/CRV.2018.00059

Shamak Dutta, B. Tripp, Graham W. Taylor

引用次数: 5

Deep Learning Object Detection Methods for Ecological Camera Trap Data 生态相机陷阱数据的深度学习目标检测方法

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-03-28 DOI: 10.1109/CRV.2018.00052

Stefan Schneider, Graham W. Taylor, S. C. Kremer

{"title":"Deep Learning Object Detection Methods for Ecological Camera Trap Data","authors":"Stefan Schneider, Graham W. Taylor, S. C. Kremer","doi":"10.1109/CRV.2018.00052","DOIUrl":"https://doi.org/10.1109/CRV.2018.00052","url":null,"abstract":"Deep learning methods for computer vision tasks show promise for automating the data analysis of camera trap images. Ecological camera traps are a common approach for monitoring an ecosystem's animal population, as they provide continual insight into an environment without being intrusive. However, the analysis of camera trap images is expensive, labour intensive, and time consuming. Recent advances in the field of deep learning for object detection show promise towards automating the analysis of camera trap images. Here, we demonstrate their capabilities by training and comparing two deep learning object detection classifiers, Faster R-CNN and YOLO v2.0, to identify, quantify, and localize animal species within camera trap images using the Reconyx Camera Trap and the self-labeled Gold Standard Snapshot Serengeti data sets. When trained on large labeled datasets, object recognition methods have shown success. We demonstrate their use, in the context of realistically sized ecological data sets, by testing if object detection methods are applicable for ecological research scenarios when utilizing transfer learning. Faster R-CNN outperformed YOLO v2.0 with average accuracies of 93.0% and 76.7% on the two data sets, respectively. Our findings show promising steps towards the automation of the labourious task of labeling camera trap images, which can be used to improve our understanding of the population dynamics of ecosystems across the planet.","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121148372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 128

Generalized Hadamard-Product Fusion Operators for Visual Question Answering 用于视觉问答的广义Hadamard-Product融合算子

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-03-26 DOI: 10.1109/CRV.2018.00016

Brendan Duke, Graham W. Taylor

引用次数: 6

Real-Time End-to-End Action Detection with Two-Stream Networks 实时端到端动作检测与两流网络

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-02-23 DOI: 10.1109/CRV.2018.00015

Alaaeldin El-Nouby, Graham W. Taylor

{"title":"Real-Time End-to-End Action Detection with Two-Stream Networks","authors":"Alaaeldin El-Nouby, Graham W. Taylor","doi":"10.1109/CRV.2018.00015","DOIUrl":"https://doi.org/10.1109/CRV.2018.00015","url":null,"abstract":"Two-stream networks have been very successful for solving the problem of action detection. However, prior work using two-stream networks train both streams separately, which prevents the network from exploiting regularities between the two streams. Moreover, unlike the visual stream, the dominant forms of optical flow computation typically do not maximally exploit GPU parallelism. We present a real-time end-to-end trainable two-stream network for action detection. First, we integrate the optical flow computation in our framework by using Flownet2. Second, we apply early fusion for the two streams and train the whole pipeline jointly end-to-end. Finally, for better network initialization, we transfer from the task of action recognition to action detection by pre-training our framework using the recently released large-scale Kinetics dataset. Our experimental results show that training the pipeline jointly end-to-end with fine-tuning the optical flow for the objective of action detection improves detection performance significantly. Additionally, we observe an improvement when initializing with parameters pre-trained using Kinetics. Last, we show that by integrating the optical flow computation, our framework is more efficient, running at real-time speeds (up to 31 fps).","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131984657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 28

Tiny SSD: A Tiny Single-Shot Detection Deep Convolutional Neural Network for Real-Time Embedded Object Detection 微型固态硬盘:用于实时嵌入式目标检测的微型单镜头检测深度卷积神经网络

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-02-19 DOI: 10.1109/CRV.2018.00023

A. Wong, M. Shafiee, Francis Li, Brendan Chwyl

{"title":"Tiny SSD: A Tiny Single-Shot Detection Deep Convolutional Neural Network for Real-Time Embedded Object Detection","authors":"A. Wong, M. Shafiee, Francis Li, Brendan Chwyl","doi":"10.1109/CRV.2018.00023","DOIUrl":"https://doi.org/10.1109/CRV.2018.00023","url":null,"abstract":"Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful techniques for tackling the challenge of object detection, one of the biggest challenges with enabling such object detection networks for widespread deployment on embedded devices is high computational and memory requirements. Recently, there has been an increasing focus in exploring small deep neural network architectures for object detection that are more suitable for embedded devices, such as Tiny YOLO and SqueezeDet. Inspired by the efficiency of the Fire microarchitecture introduced in SqueezeNet and the object detection performance of the singleshot detection macroarchitecture introduced in SSD, this paper introduces Tiny SSD, a single-shot detection deep convolutional neural network for real-time embedded object detection that is composed of a highly optimized, non-uniform Fire subnetwork stack and a non-uniform sub-network stack of highly optimized SSD-based auxiliary convolutional feature layers designed specifically to minimize model size while maintaining object detection performance. The resulting Tiny SSD possess a model size of 2.3MB (~26X smaller than Tiny YOLO) while still achieving an mAP of 61.3% on VOC 2007 (~4.2% higher than Tiny YOLO). These experimental results show that very small deep neural network architectures can be designed for real-time object detection that are well-suited for embedded scenarios.","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122362424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 127

Nature vs. Nurture: The Role of Environmental Resources in Evolutionary Deep Intelligence 先天vs.后天:环境资源在进化深度智能中的作用

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-02-09 DOI: 10.1109/CRV.2018.00058

A. Chung, P. Fieguth, A. Wong

引用次数: 1

In Defense of Classical Image Processing: Fast Depth Completion on the CPU 经典图像处理的防御:CPU上的快速深度完成

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-01-31 DOI: 10.1109/CRV.2018.00013

Jason Ku, Ali Harakeh, Steven L. Waslander

引用次数: 197

Learning a Bias Correction for Lidar-Only Motion Estimation 学习仅激光雷达运动估计的偏差校正

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2018-01-15 DOI: 10.1109/CRV.2018.00032

T. Y. Tang, David J. Yoon, F. Pomerleau, T. Barfoot

引用次数: 28

Real-Time Deep Hair Matting on Mobile Devices 移动设备上的实时深层毛发铺垫

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2017-12-19 DOI: 10.1109/CRV.2018.00011

Alex Levinshtein, Cheng Chang, Edmund Phung, I. Kezele, W. Guo, P. Aarabi

引用次数: 23

WAYLA - Generating Images from Eye Movements WAYLA——从眼球运动中生成图像

2018 15th Conference on Computer and Robot Vision (CRV) Pub Date : 2017-11-21 DOI: 10.1109/CRV.2018.00026

Bingqing Yu, James J. Clark

引用次数: 0