2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)最新文献_第9页

Multilayer Encoder-Decoder Network for 3D Nuclear Segmentation in Spheroid Models of Human Mammary Epithelial Cell Lines 人乳腺上皮细胞系球体模型三维核分割的多层编码器-解码器网络

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00300

M. Khoshdeli, G. Winkelmaier, B. Parvin

引用次数: 2

Subset Replay Based Continual Learning for Scalable Improvement of Autonomous Systems 基于子集重播的自主系统可扩展改进持续学习

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00154

P. Brahma, Adrienne Othon

引用次数: 16

Generative Adversarial Networks for Depth Map Estimation from RGB Video 基于生成对抗网络的RGB视频深度图估计

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00163

Kin Gwn Lore, K. Reddy, M. Giering, Edgar A. Bernal

{"title":"Generative Adversarial Networks for Depth Map Estimation from RGB Video","authors":"Kin Gwn Lore, K. Reddy, M. Giering, Edgar A. Bernal","doi":"10.1109/CVPRW.2018.00163","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00163","url":null,"abstract":"Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image frame, (ii) a sequence of RGB frames, and (iii) a single RGB frame plus the optical flow field computed between the frame and a neighboring frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125554960","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: 38

Learning Biomimetic Perception for Human Sensorimotor Control 人类感觉运动控制的仿生知觉学习

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00257

Masaki Nakada, Honglin Chen, Demetri Terzopoulos

引用次数: 2

Speed Estimation and Abnormality Detection from Surveillance Cameras 监控摄像机的速度估计与异常检测

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00020

Panagiotis Giannakeris, V. Kaltsa, Konstantinos Avgerinakis, A. Briassouli, S. Vrochidis, Y. Kompatsiaris

引用次数: 26

NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results 2018年全图像超分辨率挑战:方法和结果

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00130

R. Timofte, Shuhang Gu, Jiqing Wu, L. Gool

引用次数: 265

Deep Features for Recognizing Disguised Faces in the Wild 野外伪装人脸识别的深度特征

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00009

Ankan Bansal, Rajeev Ranjan, C. Castillo, R. Chellappa

引用次数: 36

It Takes Two to Tango: Cascading off-the-Shelf Face Detectors 探戈需要两个人:现成的面部检测器

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00095

Siqi Yang, A. Wiliem, B. Lovell

{"title":"It Takes Two to Tango: Cascading off-the-Shelf Face Detectors","authors":"Siqi Yang, A. Wiliem, B. Lovell","doi":"10.1109/CVPRW.2018.00095","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00095","url":null,"abstract":"Recent face detection methods have achieved high detection rates in unconstrained environments. However, as they still generate excessive false positives, any method for reducing false positives is highly desirable. This work aims to massively reduce false positives of existing face detection methods whilst maintaining the true detection rate. In addition, the proposed method also aims to sidestep the detector retraining task which generally requires enormous effort. To this end, we propose a two-stage framework which cascades two off-the-shelf face detectors. Not all face detectors can be cascaded and achieve good performance. Thus, we study three properties that allow us to determine the best pair of detectors. These three properties are: (1) correlation of true positives; (2) diversity of false positives and (3) detector runtime. Experimental results on recent large benchmark datasets such as FDDB and WIDER FACE support our findings that the false positives of a face detector could be potentially reduced by 90% whilst still maintaining high true positive detection rate. In addition, with a slight decrease in true positives, we found a pair of face detector that achieves significantly lower false positives, while being five times faster than the current state-of-the-art detector.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134178957","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: 4

Image Dehazing by Joint Estimation of Transmittance and Airlight Using Bi-Directional Consistency Loss Minimized FCN 基于双向一致性损失最小化FCN的透光率和光量联合估计图像去雾

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00137

Ranjan Mondal, Sanchayan Santra, B. Chanda

引用次数: 31

DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction 深度网络:用于单目深度预测的递归神经网络架构

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00066

Arun C. S. Kumar, S. Bhandarkar, Mukta Prasad

{"title":"DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction","authors":"Arun C. S. Kumar, S. Bhandarkar, Mukta Prasad","doi":"10.1109/CVPRW.2018.00066","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00066","url":null,"abstract":"Predicting the depth map of a scene is often a vital component of monocular SLAM pipelines. Depth prediction is fundamentally ill-posed due to the inherent ambiguity in the scene formation process. In recent times, convolutional neural networks (CNNs) that exploit scene geometric constraints have been explored extensively for supervised single-view depth prediction and semi-supervised 2-view depth prediction. In this paper we explore whether recurrent neural networks (RNNs) can learn spatio-temporally accurate monocular depth prediction from video sequences, even without explicit definition of the inter-frame geometric consistency or pose supervision. To this end, we propose a novel convolutional LSTM (ConvLSTM)-based network architecture for depth prediction from a monocular video sequence. In the proposed ConvLSTM network architecture, we harness the ability of long short-term memory (LSTM)-based RNNs to reason sequentially and predict the depth map for an image frame as a function of the appearances of scene objects in the image frame as well as image frames in its temporal neighborhood. In addition, the proposed ConvLSTM network is also shown to be able to make depth predictions for future or unseen image frame(s). We demonstrate the depth prediction performance of the proposed ConvLSTM network on the KITTI dataset and show that it gives results that are superior in terms of accuracy to those obtained via depth-supervised and self-supervised methods and comparable to those generated by state-of-the-art pose-supervised methods.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129426962","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: 75