2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)最新文献_第7页

Multi-scale Voxel Hashing and Efficient 3D Representation for Mobile Augmented Reality 移动增强现实的多尺度体素哈希和高效3D表示

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00200

Yi Xu, Yuzhang Wu, Hui Zhou

引用次数: 10

Light Field Depth Estimation on Off-the-Shelf Mobile GPU 基于现成移动GPU的光场深度估计

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00106

Andre Ivan, Williem, I. Park

{"title":"Light Field Depth Estimation on Off-the-Shelf Mobile GPU","authors":"Andre Ivan, Williem, I. Park","doi":"10.1109/CVPRW.2018.00106","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00106","url":null,"abstract":"While novel light processing algorithms have been continuously introduced, it is still challenging to perform light field processing on a mobile device with limited computation resource due to the high dimensionality of light field data. Recently, the performance of mobile graphics processing unit (GPU) increases rapidly and GPGPU on mobile GPU utilizes massive parallel computation to solve various computer vision problems with high computational complexity. To show the potential capability of light field processing on mobile GPU, we parallelize and optimize the state-of-the-art light field depth estimation which is essential to many light field applications. We employ both algorithm and kernel-based optimization to enable light field processing on mobile GPU. Light field processing involves independent pixel processing with intensive floating-point operations that can be vectorized to match single instruction multiple data (SIMD) style of GPU architecture. We design efficient memory access, caching, and prefetching to exploit light field properties. The experimental result shows that the light field depth estimation on mobile GPU obtains comparable performance as on the desktop CPU. The proposed optimization method gains up to 25 times speedup compared to the naïve baseline method.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"34 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":"122145806","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: 2

Hard Example Mining with Auxiliary Embeddings 使用辅助嵌入的硬示例挖掘

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00013

Evgeny Smirnov, A. Melnikov, A. Oleinik, Elizaveta Ivanova, I. Kalinovskiy, Eugene Luckyanets

{"title":"Hard Example Mining with Auxiliary Embeddings","authors":"Evgeny Smirnov, A. Melnikov, A. Oleinik, Elizaveta Ivanova, I. Kalinovskiy, Eugene Luckyanets","doi":"10.1109/CVPRW.2018.00013","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00013","url":null,"abstract":"Hard example mining is an important part of the deep embedding learning. Most methods perform it at the mini-batch level. However, in the large-scale settings there is only a small chance that proper examples will appear in the same mini-batch and will be coupled into the hard example pairs or triplets. Doppelganger mining was previously proposed to increase this chance by means of class-wise similarity. This method ensures that examples of similar classes are sampled into the same mini-batch together. One of the drawbacks of this method is that it operates only at the class level, while there also might be a way to select appropriate examples within class in a more elaborated way than randomly. In this paper, we propose to use auxiliary embeddings for hard example mining. These embeddings are constructed in such way that similar examples have close embeddings in the cosine similarity sense. With the help of these embeddings it is possible to select new examples for the mini-batch based on their similarity with the already selected examples. We propose several ways to create auxiliary embeddings and use them to increase the number of potentially hard positive and negative examples in each mini-batch. Our experiments on the challenging Disguised Faces in the Wild (DFW) dataset show that hard example mining with auxiliary embeddings improves the discriminative power of learned representations.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"118 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":"127028431","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: 36

Challenges on Large Scale Surveillance Video Analysis 大规模监控视频分析面临的挑战

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00017

Weitao Feng, Deyi Ji, Yiru Wang, Shuorong Chang, Hansheng Ren, Weihao Gan

{"title":"Challenges on Large Scale Surveillance Video Analysis","authors":"Weitao Feng, Deyi Ji, Yiru Wang, Shuorong Chang, Hansheng Ren, Weihao Gan","doi":"10.1109/CVPRW.2018.00017","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00017","url":null,"abstract":"Large scale surveillance video analysis is one of the most important components in the future artificial intelligent city. It is a very challenging but practical system, consists of multiple functionalities such as object detection, tracking, identification and behavior analysis. In this paper, we try to address three tasks hosted in NVIDIA AI City Challenge contest. First, a system that transforming the image coordinate to world coordinate has been proposed, which is useful to estimate the vehicle speed on the road. Second, anomalies like car crash event and stalled vehicles can be found by the proposed anomaly detector framework. Third, multiple camera vehicle re-identification problem has been investigated and a matching algorithm is explained. All these tasks are based on our proposed online single camera multiple object tracking (MOT) system, which has been evaluated on the widely used MOT16 challenge benchmark. We show that it achieves the best performance compared to the state-of-the-art methods. Besides of MOT, we evaluate the proposed vehicle re-identification model on VeRi-776 dataset and it outperforms all other methods with a large margin.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"63 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":"127098428","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

Residual Inception Skip Network for Binary Segmentation 二值分割的残差初始跳变网络

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00037

Jigar Doshi

引用次数: 20

Advertisement Effectiveness Estimation Based on Crowdsourced Multimodal Affective Responses 基于众包多模态情感反应的广告效果评估

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00173

Genki Okada, Kenta Masui, N. Tsumura

引用次数: 14

Face Verification with Disguise Variations via Deep Disguise Recognizer 基于深度伪装识别器的伪装变异人脸验证

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00010

Naman Kohli, Daksha Yadav, A. Noore

引用次数: 17

Cell Image Segmentation by Integrating Multiple CNNs 集成多个cnn的细胞图像分割

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00296

Yuki Hiramatsu, K. Hotta, Ayako Imanishi, M. Matsuda, Kenta Terai

引用次数: 16

Unsupervised Vehicle Re-identification Using Triplet Networks 使用三重网络的无监督车辆再识别

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00030

Pedro A. Marín-Reyes, Andrea Palazzi, Luca Bergamini, S. Calderara, J. Lorenzo-Navarro, R. Cucchiara

{"title":"Unsupervised Vehicle Re-identification Using Triplet Networks","authors":"Pedro A. Marín-Reyes, Andrea Palazzi, Luca Bergamini, S. Calderara, J. Lorenzo-Navarro, R. Cucchiara","doi":"10.1109/CVPRW.2018.00030","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00030","url":null,"abstract":"Vehicle re-identification plays a major role in modern smart surveillance systems. Specifically, the task requires the capability to predict the identity of a given vehicle, given a dataset of known associations, collected from different views and surveillance cameras. Generally, it can be cast as a ranking problem: given a probe image of a vehicle, the model needs to rank all database images based on their similarities w.r.t the probe image. In line with recent research, we devise a metric learning model that employs a supervision based on local constraints. In particular, we leverage pairwise and triplet constraints for training a network capable of assigning a high degree of similarity to samples sharing the same identity, while keeping different identities distant in feature space. Eventually, we show how vehicle tracking can be exploited to automatically generate a weakly labelled dataset that can be used to train the deep network for the task of vehicle re-identification. Learning and evaluation is carried out on the NVIDIA AI city challenge videos.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"430 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121162209","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: 29

2D-3D CNN Based Architectures for Spectral Reconstruction from RGB Images 基于2D-3D CNN的RGB图像光谱重建架构

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2018-06-01 DOI: 10.1109/CVPRW.2018.00129

Sriharsha Koundinya, Himanshu Sharma, Manoj Sharma, Avinash Upadhyay, Raunak Manekar, Rudrabha Mukhopadhyay, A. Karmakar, S. Chaudhury

{"title":"2D-3D CNN Based Architectures for Spectral Reconstruction from RGB Images","authors":"Sriharsha Koundinya, Himanshu Sharma, Manoj Sharma, Avinash Upadhyay, Raunak Manekar, Rudrabha Mukhopadhyay, A. Karmakar, S. Chaudhury","doi":"10.1109/CVPRW.2018.00129","DOIUrl":"https://doi.org/10.1109/CVPRW.2018.00129","url":null,"abstract":"Hyperspectral cameras are used to preserve fine spectral details of scenes that are not captured by traditional RGB cameras that comprehensively quantizes radiance in RGB images. Spectral details provide additional information that improves the performance of numerous image based analytic applications, but due to high hyperspectral hardware cost and associated physical constraints, hyperspectral images are not easily available for further processing. Motivated by the performance of deep learning for various computer vision applications, we propose a 2D convolution neural network and a 3D convolution neural network based approaches for hyperspectral image reconstruction from RGB images. A 2D-CNN model primarily focuses on extracting spectral data by considering only spatial correlation of the channels in the image, while in 3D-CNN model the inter-channel co-relation is also exploited to refine the extraction of spectral data. Our 3D-CNN based architecture achieves very good performance in terms of MRAE and RMSE. In contrast to 3D-CNN, our 2D-CNN based architecture also achieves comparable performance with very less computational complexity.","PeriodicalId":150600,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"15 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":"129004725","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: 42