2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)最新文献_第3页

Increasing Video Saliency Model Generalizability by Training for Smooth Pursuit Prediction 通过训练提高视频显著性模型的泛化性，用于平滑追踪预测

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00264

Mikhail Startsev, M. Dorr

引用次数: 5

Covariance Matrices Encoding Based on the Log-Euclidean and Affine Invariant Riemannian Metrics 基于对数欧几里德和仿射不变黎曼度量的协方差矩阵编码

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00080

Ioana Ilea, L. Bombrun, S. Said, Y. Berthoumieu

引用次数: 8

RPIfield: A New Dataset for Temporally Evaluating Person Re-identification RPIfield:一个用于时间评估人员再识别的新数据集

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00251

Meng Zheng, S. Karanam, R. Radke

{"title":"RPIfield: A New Dataset for Temporally Evaluating Person Re-identification","authors":"Meng Zheng, S. Karanam, R. Radke","doi":"10.1109/CVPRW.2018.00251","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00251","url":null,"abstract":"The operational aspects of real-world human re-identification are typically oversimplified in academic research. Specifically, re-id algorithms are evaluated by matching probe images to candidates from a fixed gallery collected at the end of a video, ignoring the arrival time of each candidate. However, in real-world applications like crime prevention, a re-id system would likely operate in real time, and might be in continuous operation for several days. It would be natural to provide the user of such a system with instantaneous ranked lists from the current gallery candidates rather than waiting for a collective list after processing the whole video sequence. Re-id algorithms thus need to be evaluated based on their temporal performance on a dynamic gallery populated by an increasing number of candidates (some of whom may return several times over a long duration). This aspect of the problem is difficult to study with current benchmarking re-id datasets since they lack time-stamp information. In this paper, we introduce a new multi-shot re-id dataset, called RPIfield, which provides explicit time-stamp information for each candidate. The RPIfield dataset is comprised of 12 outdoor camera videos, with 112 known actors walking along pre-specified paths among about 4000 distractors. Each actor in RPIfield has multiple reappearances in one or more camera views, which allows the study of re-id algorithms in a more general context, especially with respect to temporal aspects.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"157 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133686538","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: 21

Implementing a Robust Explanatory Bias in a Person Re-identification Network 在人再识别网络中实现稳健的解释偏差

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00291

Esube Bekele, W. Lawson, Z. Horne, S. Khemlani

{"title":"Implementing a Robust Explanatory Bias in a Person Re-identification Network","authors":"Esube Bekele, W. Lawson, Z. Horne, S. Khemlani","doi":"10.1109/CVPRW.2018.00291","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00291","url":null,"abstract":"Deep learning improved attributes recognition significantly in recent years. However, many of these networks remain \"black boxes\" and providing a meaningful explanation of their decisions is a major challenge. When these networks misidentify a person, they should be able to explain this mistake. The ability to generate explanations compelling enough to serve as useful accounts of the system's operations at a very high human-level is still in its infancy. In this paper, we utilize person re-identification (re-ID) networks as a platform to generate explanations. We propose and implement a framework that can be used to explain person re-ID using soft-biometric attributes. In particular, the resulting framework embodies a cognitively validated explanatory bias: people prefer and produce explanations that concern inherent properties instead of extrinsic influences. This bias is pervasive in that it affects the fitness of explanations across a broad swath of contexts, particularly those that concern conflicting or anomalous observations. To explain person re-ID, we developed a multiattribute residual network that treats a subset of its features as either inherent or extrinsic. Using these attributes, the system generates explanations based on inherent properties when the similarity of two input images is low, and it generates explanations based on extrinsic properties when the similarity is high. We argue that such a framework provides a blueprint for how to make the decisions of deep networks comprehensible to human operators. As an intermediate step, we demonstrate state-of-the-art attribute recognition performance on two pedestrian datasets (PETA and PA100K) and a face-based attribute dataset (CelebA). The VIPeR dataset is then used to generate explanations for re-ID with a network trained on PETA attributes.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"177 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":"124403935","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: 5

Relating Deep Neural Network Representations to EEG-fMRI Spatiotemporal Dynamics in a Perceptual Decision-Making Task 感知决策任务中深层神经网络表征与EEG-fMRI时空动态的关系

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00267

Tao Tu, Jonathan Koss, P. Sajda

引用次数: 8

Estimation of Center of Mass for Sports Scene Using Weighted Visual Hull 基于加权视觉船体的运动场景质心估计

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00234

Tomoya Kaichi, Shohei Mori, H. Saito, Kosuke Takahashi, Dan Mikami, Mariko Isogawa, H. Kimata

{"title":"Estimation of Center of Mass for Sports Scene Using Weighted Visual Hull","authors":"Tomoya Kaichi, Shohei Mori, H. Saito, Kosuke Takahashi, Dan Mikami, Mariko Isogawa, H. Kimata","doi":"10.1109/CVPRW.2018.00234","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00234","url":null,"abstract":"This paper presents a method to estimate the 3D position of a center of mass (CoM) of a human body from a set of multi-view images. As a well-known fact, in sports, collections of CoM are important for analyzing the athletes' performance. Most conventional studies in CoM estimation require installing a measuring system (e.g., a force plate or optical motion capture system) or attaching sensors to the athlete. While such systems reliably estimate CoM, casual settings are preferable for simplifying preparations. To address this issue, the proposed method takes a vision-based approach that does not require specialized hardware and wearable devices. Our method calculates subject's CoM using voxels with body parts dependent weighting. This individual voxel reconstruction and voxel-wise weighting reflects the differences in each body shape, and are expected to contribute to higher performance in analysis. The results using real data demonstrated the performance of the proposed method were compared to force plate data, and provided a 3D CoM visualization in a dynamic scene.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"19 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":"116925826","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: 9

Traffic Speed Estimation from Surveillance Video Data: For the 2nd NVIDIA AI City Challenge Track 1 基于监控视频数据的交通速度估计:第二届NVIDIA AI城市挑战赛

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00029

Tingting Huang

引用次数: 9

Monocular RGB Hand Pose Inference from Unsupervised Refinable Nets 基于无监督精细网络的单目RGB手部姿态推断

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00155

E. Dibra, Silvan Melchior, A. Balkis, Thomas Wolf, C. Öztireli, M. Gross

引用次数: 17

Latent Fingerprint Image Quality Assessment Using Deep Learning 基于深度学习的潜在指纹图像质量评估

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00092

J. Ezeobiejesi, B. Bhanu

引用次数: 14

Exploring the Feasibility of Face Video Based Instantaneous Heart-Rate for Micro-Expression Spotting 探索基于人脸视频的瞬时心率微表情识别的可行性

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00179

Puneet Gupta, B. Bhowmick, A. Pal

{"title":"Exploring the Feasibility of Face Video Based Instantaneous Heart-Rate for Micro-Expression Spotting","authors":"Puneet Gupta, B. Bhowmick, A. Pal","doi":"10.1109/CVPRW.2018.00179","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00179","url":null,"abstract":"Facial micro-expressions (ME) are manifested by human reflexive behavior and thus they are useful to disclose the genuine human emotions. Their analysis plays a pivotal role in many real-world applications encompassing affective computing, biometrics and psychotherapy. The first and foremost step for ME analysis is ME spotting which refers to detection of ME affected frames from a video. ME spotting is a highly challenging research problem and even human experts cannot correctly perform it because MEs are manifested using subtle face deformations and that too for a short duration. It is well established that changes in the human emotions, not only manifest ME but it also introduces changes in instantaneous heart rate. Thus, the manifestation of ME and changes in the instantaneous heart rate are related to the change in human expressions and both of them are estimated using temporal deformations of the face. This provides the motivation of this paper that aims to explore the feasibility of variations in the instantaneous heart rate for performing the correct the ME spotting. Experimental results conducted on a publicly available spontaneous ME spotting dataset, reveal that the variations in instantaneous heart rate can be utilized to improve the ME spotting.","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":"129342347","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: 14