IEEE Transactions on Image Processing最新文献_第7页

Semi-Supervised Human Detection via Region Proposal Networks Aided by Verification. 通过验证辅助区域建议网络进行半监督式人体检测

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-10-03 DOI: 10.1109/TIP.2019.2944306

Si Wu, Wenhao Wu, Shiyao Lei, Sihao Lin, Rui Li, Zhiwen Yu, Hau-San Wong

{"title":"Semi-Supervised Human Detection via Region Proposal Networks Aided by Verification.","authors":"Si Wu, Wenhao Wu, Shiyao Lei, Sihao Lin, Rui Li, Zhiwen Yu, Hau-San Wong","doi":"10.1109/TIP.2019.2944306","DOIUrl":"10.1109/TIP.2019.2944306","url":null,"abstract":"In this paper, we explore how to leverage readily available unlabeled data to improve semi-supervised human detection performance. For this purpose, we specifically modify the region proposal network (RPN) for learning on a partially labeled dataset. Based on commonly observed false positive types, a verification module is developed to assess foreground human objects in the candidate regions to provide an important cue for filtering the RPN's proposals. The remaining proposals with high confidence scores are then used as pseudo annotations for re-training our detection model. To reduce the risk of error propagation in the training process, we adopt a self-paced training strategy to progressively include more pseudo annotations generated by the previous model over multiple training rounds. The resulting detector re-trained on the augmented data can be expected to have better detection performance. The effectiveness of the main components of this framework is verified through extensive experiments, and the proposed approach achieves state-of-the-art detection results on multiple scene-specific human detection benchmarks in the semi-supervised setting.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62589764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Interleaved Cascade of Shrinkage Fields for Joint Image Dehazing and Denoising. 为联合图像去污和去噪学习交错级联收缩场

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-30 DOI: 10.1109/TIP.2019.2942504

Qingbo Wu, Wenqi Ren, Xiaochun Cao

引用次数: 0

A Biological Vision Inspired Framework for Image Enhancement in Poor Visibility Conditions. 在能见度较低的条件下增强图像的生物视觉启发框架。

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-25 DOI: 10.1109/TIP.2019.2938310

Kai-Fu Yang, Xian-Shi Zhang, Yong-Jie Li

{"title":"A Biological Vision Inspired Framework for Image Enhancement in Poor Visibility Conditions.","authors":"Kai-Fu Yang, Xian-Shi Zhang, Yong-Jie Li","doi":"10.1109/TIP.2019.2938310","DOIUrl":"10.1109/TIP.2019.2938310","url":null,"abstract":"Image enhancement is an important pre-processing step for many computer vision applications especially regarding the scenes in poor visibility conditions. In this work, we develop a unified two-pathway model inspired by the biological vision, especially the early visual mechanisms, which contributes to image enhancement tasks including low dynamic range (LDR) image enhancement and high dynamic range (HDR) image tone mapping. Firstly, the input image is separated and sent into two visual pathways: structure-pathway and detail-pathway, corresponding to the M-and P-pathway in the early visual system, which code the low-and high-frequency visual information, respectively. In the structure-pathway, an extended biological normalization model is used to integrate the global and local luminance adaptation, which can handle the visual scenes with varying illuminations. On the other hand, the detail enhancement and local noise suppression are achieved in the detail-pathway based on local energy weighting. Finally, the outputs of structure-and detail-pathway are integrated to achieve the low-light image enhancement. In addition, the proposed model can also be used for tone mapping of HDR images with some fine-tuning steps. Extensive experiments on three datasets (two LDR image datasets and one HDR scene dataset) show that the proposed model can handle the visual enhancement tasks mentioned above efficiently and outperform the related state-of-the-art methods.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62586368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Receptive Field Size vs. Model Depth for Single Image Super-resolution. 单张图像超分辨率的感受野大小与模型深度的关系

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-25 DOI: 10.1109/TIP.2019.2941327

Ruxin Wang, Mingming Gong, Dacheng Tao

引用次数: 0

Intermediate Deep Feature Compression: Toward Intelligent Sensing. 中间深度特征压缩：迈向智能传感

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-25 DOI: 10.1109/TIP.2019.2941660

Zhuo Chen, Kui Fan, Shiqi Wang, Lingyu Duan, Weisi Lin, Alex C Kot

{"title":"Intermediate Deep Feature Compression: Toward Intelligent Sensing.","authors":"Zhuo Chen, Kui Fan, Shiqi Wang, Lingyu Duan, Weisi Lin, Alex C Kot","doi":"10.1109/TIP.2019.2941660","DOIUrl":"10.1109/TIP.2019.2941660","url":null,"abstract":"The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and transmitting visual signals or the ultimately utilized top-layer deep learning features, we propose to compactly represent and convey the intermediate-layer deep learning features with high generalization capability, to facilitate the collaborating approach between front and cloud ends. This strategy enables a good balance among the computational load, transmission load and the generalization ability for cloud servers when deploying the deep neural networks for large scale cloud based visual analysis. Moreover, the presented strategy also makes the standardization of deep feature coding more feasible and promising, as a series of tasks can simultaneously benefit from the transmitted intermediate layer features. We also present the results for evaluations of both lossless and lossy deep feature compression, which provide meaningful investigations and baselines for future research and standardization activities.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62587991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards weakly-supervised focus region detection via recurrent constraint network. 通过递归约束网络实现弱监督焦点区域检测

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-25 DOI: 10.1109/TIP.2019.2942505

Wenda Zhao, Xueqing Hou, Xiaobing Yu, You He, Huchuan Lu

{"title":"Towards weakly-supervised focus region detection via recurrent constraint network.","authors":"Wenda Zhao, Xueqing Hou, Xiaobing Yu, You He, Huchuan Lu","doi":"10.1109/TIP.2019.2942505","DOIUrl":"10.1109/TIP.2019.2942505","url":null,"abstract":"Recent state-of-the-art methods on focus region detection (FRD) rely on deep convolutional networks trained with costly pixel-level annotations. In this study, we propose a FRD method that achieves competitive accuracies but only uses easily obtained bounding box annotations. Box-level tags provide important cues of focus regions but lose the boundary delineation of the transition area. A recurrent constraint network (RCN) is introduced for this challenge. In our static training, RCN is jointly trained with a fully convolutional network (FCN) through box-level supervision. The RCN can generate a detailed focus map to locate the boundary of the transition area effectively. In our dynamic training, we iterate between fine-tuning FCN and RCN with the generated pixel-level tags and generate finer new pixel-level tags. To boost the performance further, a guided conditional random field is developed to improve the quality of the generated pixel-level tags. To promote further study of the weakly supervised FRD methods, we construct a new dataset called FocusBox, which consists of 5000 challenging images with bounding box-level labels. Experimental results on existing datasets demonstrate that our method not only yields comparable results than fully supervised counterparts but also achieves a faster speed.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62588586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Spatial and Temporal Network for Robust Visual Object Tracking. 用于稳健视觉对象跟踪的深度时空网络

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-25 DOI: 10.1109/TIP.2019.2942502

Zhu Teng, Junliang Xing, Qiang Wang, Baopeng Zhang, Jianping Fan

{"title":"Deep Spatial and Temporal Network for Robust Visual Object Tracking.","authors":"Zhu Teng, Junliang Xing, Qiang Wang, Baopeng Zhang, Jianping Fan","doi":"10.1109/TIP.2019.2942502","DOIUrl":"10.1109/TIP.2019.2942502","url":null,"abstract":"There are two key components that can be leveraged for visual tracking: (a) object appearances; and (b) object motions. Many existing techniques have recently employed deep learning to enhance visual tracking due to its superior representation power and strong learning ability, where most of them employed object appearances but few of them exploited object motions. In this work, a deep spatial and temporal network (DSTN) is developed for visual tracking by explicitly exploiting both the object representations from each frame and their dynamics along multiple frames in a video, such that it can seamlessly integrate the object appearances with their motions to produce compact object appearances and capture their temporal variations effectively. Our DSTN method, which is deployed into a tracking pipeline in a coarse-to-fine form, can perceive the subtle differences on spatial and temporal variations of the target (object being tracked), and thus it benefits from both off-line training and online fine-tuning. We have also conducted our experiments over four largest tracking benchmarks, including OTB-2013, OTB-2015, VOT2015, and VOT2017, and our experimental results have demonstrated that our DSTN method can achieve competitive performance as compared with the state-of-the-art techniques. The source code, trained models, and all the experimental results of this work will be made public available to facilitate further studies on this problem.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62588807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Collective Affinity Learning for Partial Cross-Modal Hashing. 部分跨模态哈希的集体亲和学习。

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-23 DOI: 10.1109/TIP.2019.2941858

Jun Guo, Wenwu Zhu

{"title":"Collective Affinity Learning for Partial Cross-Modal Hashing.","authors":"Jun Guo, Wenwu Zhu","doi":"10.1109/TIP.2019.2941858","DOIUrl":"10.1109/TIP.2019.2941858","url":null,"abstract":"In the past decade, various unsupervised hashing methods have been developed for cross-modal retrieval. However, in real-world applications, it is often the incomplete case that every modality of data may suffer from some missing samples. Most existing works assume that every object appears in both modalities, hence they may not work well for partial multi-modal data. To address this problem, we propose a novel Collective Affinity Learning Method (CALM), which collectively and adaptively learns an anchor graph for generating binary codes on partial multi-modal data. In CALM, we first construct modality-specific bipartite graphs collectively, and derive a probabilistic model to figure out complete data-to-anchor affinities for each modality. Theoretical analysis reveals its ability to recover missing adjacency information. Moreover, a robust model is proposed to fuse these modality-specific affinities by adaptively learning a unified anchor graph. Then, the neighborhood information from the learned anchor graph acts as feedback, which guides the previous affinity reconstruction procedure. To solve the formulated optimization problem, we further develop an effective algorithm with linear time complexity and fast convergence. Last, Anchor Graph Hashing (AGH) is conducted on the fused affinities for cross-modal retrieval. Experimental results on benchmark datasets show that our proposed CALM consistently outperforms the existing methods.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62588314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Low-rank quaternion approximation for color image processing. 用于彩色图像处理的低秩四元近似法

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-19 DOI: 10.1109/TIP.2019.2941319

Yongyong Chen, Xiaolin Xiao, Yicong Zhou

{"title":"Low-rank quaternion approximation for color image processing.","authors":"Yongyong Chen, Xiaolin Xiao, Yicong Zhou","doi":"10.1109/TIP.2019.2941319","DOIUrl":"10.1109/TIP.2019.2941319","url":null,"abstract":"Low-rank matrix approximation (LRMA)-based methods have made a great success for grayscale image processing. When handling color images, LRMA either restores each color channel independently using the monochromatic model or processes the concatenation of three color channels using the concatenation model. However, these two schemes may not make full use of the high correlation among RGB channels. To address this issue, we propose a novel low-rank quaternion approximation (LRQA) model. It contains two major components: first, instead of modeling a color image pixel as a scalar in conventional sparse representation and LRMA-based methods, the color image is encoded as a pure quaternion matrix, such that the cross-channel correlation of color channels can be well exploited; second, LRQA imposes the low-rank constraint on the constructed quaternion matrix. To better estimate the singular values of the underlying low-rank quaternion matrix from its noisy observation, a general model for LRQA is proposed based on several nonconvex functions. Extensive evaluations for color image denoising and inpainting tasks verify that LRQA achieves better performance over several state-of-the-art sparse representation and LRMA-based methods in terms of both quantitative metrics and visual quality.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62587764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Noise-Robust Iterative Back-Projection. 噪声抑制迭代反投影

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-09-16 DOI: 10.1109/TIP.2019.2940414

Jun-Sang Yoo, Jong-Ok Kim

{"title":"Noise-Robust Iterative Back-Projection.","authors":"Jun-Sang Yoo, Jong-Ok Kim","doi":"10.1109/TIP.2019.2940414","DOIUrl":"10.1109/TIP.2019.2940414","url":null,"abstract":"Noisy image super-resolution (SR) is a significant challenging process due to the smoothness caused by denoising. Iterative back-projection (IBP) can be helpful in further enhancing the reconstructed SR image, but there is no clean reference image available. This paper proposes a novel back-projection algorithm for noisy image SR. Its main goal is to pursuit the consistency between LR and SR images. We aim to estimate the clean reconstruction error to be back-projected, using the noisy and denoised reconstruction errors. We formulate a new cost function on the principal component analysis (PCA) transform domain to estimate the clean reconstruction error. In the data term of the cost function, noisy and denoised reconstruction errors are combined in a region-adaptive manner using texture probability. In addition, the sparsity constraint is incorporated into the regularization term, based on the Laplacian characteristics of the reconstruction error. Finally, we propose an eigenvector estimation method to minimize the effect of noise. The experimental results demonstrate that the proposed method can perform back-projection in a more noise-robust manner than the conventional IBP, and harmoniously work with any other SR methods as a post-processing.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"29 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2019-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62587355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0