检索结果-内蒙古大学图书馆

Discovering Primary objects in Videos by Saliency Fusion and Iterative Appearance Estimation

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2016年第6期26卷 1070-1083页

作者： Yang, Jiong Zhao, Gangqiang Yuan, Junsong Shen, Xiaohui Lin, Zhe Price, Brian Brandt, Jonathan Nanyang Technol Univ Rapid Rich Object Search Lab Singapore 637553 Singapore Nanyang Technol Univ Dept Elect & Elect Engn Singapore 639798 Singapore Adobe Res San Jose CA 95110 USA

In this paper, we propose a new method for detecting primary objects in unconstrained videos in a completely automatic setting. Here, we define the primary object in a video as the object that presents saliently in most of the frames. Unlike previous works considering only local saliency detection or common pattern discovery, the proposed method integrates the local visual/motion saliency extracted from each frame, global appearance consistency throughout the video, and spatiotemporal smoothness constraint on object trajectories. We first identify a temporal coherent salient region throughout the whole video, and then explicitly learn a global appearance model to distinguish the primary object against the background. In order to obtain high-quality saliency estimations from both appearance and motion cues, we propose a novel self-adaptive saliency map fusion method by learning the reliability of saliency maps from labeled data. As a whole, our method can robustly localize and track primary objects in diverse video content, and handle the challenges such as fast object and camera motion, large scale and appearance variation, background clutter, and pose deformation. Moreover, compared with some existing approaches that assume the object is present in all the frames, our approach can naturally handle the case where the object is present only in part of the frames, e.g., the object enters the scene in the middle of the video or leaves the scene before the video ends. We also propose a new video data set containing 51 videos for primary object detection with per-frame ground-truth labeling. Quantitative experiments on several challenging video data sets demonstrate the superiority of our method compared with the recent state of the arts.

关键词： Appearance model automatic object detection primary object saliency fusion

来源：评论

学校读者我要写书评

暂无评论

Multitask Person Re-Identification using Homoscedastic Uncertainty Learning

Multitask Person Re-Identification using Homoscedastic Uncer...

引用

IEEE International Symposium on Circuits and Systems (IEEE ISCAS)

作者： Tay, Chiat-Pin Roy, Sharmili Yap, Kim-Hui Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Nanyang Technol Univ Rapid Rich Object Search Lab Singapore Singapore

ISBN: (纸本)9781728103976

In this paper, we propose a new multitask neural network called Part Attribute Loss Net (PALNet) for person re-identification (re-id) with homoscedastic uncertainty learning. Currently, many person re-id algorithms use person identity as the main ground truth information to train and to perform prediction task. This single task approach is simple to setup but usually provides poor generalization performance. Some other person re-id works [1] [2] incorporate additional cues such as body parts to improve the learned representations. However, this requires additional body part annotations. Person attributes, which are present in some of the large person re-id datasets like Market1501 [3] and DukeMTMC-reID [4], are not used. Furthermore, the multitask networks found in some of the recent works use heuristic approach in weighing their task losses. Our PALNet seeks to address these issues by leveraging on person identity classification, body part detection and person attribute prediction, all built into a unified network. We also incorporate the homoscedastic uncertainty learning to automatically determine the weighing of the loss function of the different tasks. The PALNet consists of three tasks, with person identity classification as the main task. The body part detection and person attributes are two sub tasks to share different learning experience with the main task. The uncertainty learning provide us good indication of the observable task noises and allows us to optimize the accuracy performance without the time consuming grid search method. When benchmarking on DukeMTMC-reID dataset [4], our approach outperforms other state-of-the-art methods. On Market1501 dataset [3], we are on par with the best state-of-the-art method but outperforms the rest by at least 6.4% mAP and 3.5% Rank-1 accuracy. These results are reported without re-ranking.

关键词： Task analysis Feature extraction Uncertainty Training Deep learning Computer architecture Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Image quality assessment based on multi-scale representation of structure

引用

DIGITAL SIGNAL PROCESSING 2014年 33卷 125-133页

作者： Qian, Jiansheng Wu, Dong Li, Leida Cheng, Deqiang Wang, Xuesong China Univ Min & Technol Sch Informat & Elect Engn Xuzhou 221116 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Rapid Rich Object Search ROSE Lab Singapore 639798 Singapore

This paper presents an image quality assessment algorithm using representation of image structures in scale space. It is based on the finding that difference-of-Gaussian (DOG) can capture the structures of an image with flexibility and it is sensitive to image degradations. A set of DoG signals are first computed to represent the image structures at different octaves and scales. A coarse quality score is calculated by comparing the DoG signals between the reference image and test image at each octave and scale. Information content weighting is then incorporated to generate the final quality score. Experimental results on five singly-distorted databases and the laboratory for Image and Video Engineering (LIVE) multiply-distorted database show the effectiveness of the proposed method. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Image quality assessment Full-reference Difference-of-Gaussian Information content weighting

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding 33

Heterogeneous Transfer Learning via Deep Matrix Completion w...

引用

33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence

作者： Li, Haoliang Pan, Sinno Jialin Wan, Renjie Kot, Alex C. Nanyang Technol Univ Rapid Rich Object Search ROSE Lab Singapore Singapore Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore

ISBN: (纸本)9781577358091

Heterogeneous Transfer Learning (HTL) aims to solve transfer learning problems where a source domain and a target domain are of heterogeneous types of features. Most existing HTL approaches either explicitly learn feature mappings between the heterogeneous domains or implicitly reconstruct heterogeneous cross-domain features based on matrix completion techniques. In this paper, we propose a new HTL method based on a deep matrix completion framework, where kernel embedding of distributions is trained in an adversarial manner for learning heterogeneous features across domains. We conduct extensive experiments on two different vision tasks to demonstrate the effectiveness of our proposed method compared with a number of baseline methods.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Improving Robustness of DNNs against Common Corruptions via Gaussian Adversarial Training

Improving Robustness of DNNs against Common Corruptions via ...

引用

IEEE International Conference on Visual Communications and Image Processing (VCIP)

作者： Yi, Chenyu Li, Haoliang Wan, Renjie Kot, Alex C. Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Nanyang Technol Univ Rapid Rich Object Search ROSE Lab Singapore Singapore

ISBN: (纸本)9781728180687

Deep neural networks have demonstrated tremendous success in image classification, but their performance sharply degrades when evaluated on slightly different test data (e.g., data with corruptions). To address these issues, we propose a minimax approach to improve common corruption robustness of deep neural networks via Gaussian Adversarial Training. To be specific, we propose to train neural networks with adversarial examples where the perturbations are Gaussian-distributed. Our experiments show that our proposed GAT can improve neural networks' robustness to noise corruptions more than other baseline methods. It also outperforms the state-of-the-art method in improving the overall robustness to common corruptions.

关键词： Deep Learning Robustness to Common Corruptions Adversarial Training Data Augmentation

来源：评论

学校读者我要写书评

暂无评论

AANet: Attribute Attention Network for Person Re-Identifications 32

AANet: Attribute Attention Network for Person Re-Identificat...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tay, Chiat-Pin Roy, Sharmili Yap, Kim-Hui Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Nanyang Technol Univ Rapid Rich Object Search Lab Singapore Singapore

ISBN: (纸本)9781728132938

This paper proposes Attribute Attention Network (AANet), a new architecture that integrates person attributes and attribute attention maps into a classification framework to solve the person re-identification (re-ID) problem. Many person re-ID models typically employ semantic cues such as body parts or human pose to improve the re-ID performance. Attribute information, however, is often not utilized. The proposed AANet leverages on a baseline model that uses body parts and integrates the key attribute information in an unified learning framework. The AANet consists of a global person ID task, a part detection task and a crucial attribute detection task. By estimating the class responses of individual attributes and combining them to form the attribute attention map (AAM), a very strong discriminatory representation is constructed. The proposed AANet outperforms the best state-of-the-art method [20] using ResNet-50 by 3.36% in mAP and 3.12% in Rank-1 accuracy on DukeMTMC-reID dataset. On Market1501 dataset, AANet achieves 92.38% mAP and 95.10% Rank-1 accuracy with re-ranking, outperforming [11], another state of the art method using ResNet-152, by 1.42% in mAP and 0.47% in Rank-1 accuracy. In addition, AANet can perform person attribute prediction (e.g., gender hair length, clothing length etc.), and localize the attributes in the query image.

关键词： Categorization Deep Learning Recognition: Detection Representation Learning Retrieval

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Tuning Sparse Fast Fourier Transform 18th

An Adaptive Tuning Sparse Fast Fourier Transform

引用

18th Pacific-Rim Conference on Multimedia (PCM)

作者： Shi, Sheng Yang, Runkai Zhang, Xinfeng You, Haihang Fan, Dongrui Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Nanyang Technol Univ Rapid Rich Object Search Lab Singapore Singapore

ISBN: (纸本)9783319773834;9783319773827

The Sparse Fast Fourier Transform (SFFT) is a novel algorithm for discrete Fourier transforms on signals with the sparsity in frequency domain. A reference implementation of the algorithm has been proven to be faster than modern FFT library in cases of sufficient sparsity. However, the SFFT implementation has the drawback that it only works reliably for very specific input parameters, especially signal sparsity k. This drawback hinders the extensive applications of SFFT. In this paper, we present a newAdaptiveTuning Sparse Fast FourierTransform (ATSFFT). In the case of unknown sparsity k, ATSFFT can probe the sparsity k via adaptive dynamic tuning technology and then complete the Fourier transform of signal. Experimental results show that ATSFFT not only can control the error better than SFFT, but also performs faster than SFFT, which computes more efficiently than the state-of-the-art FFTW.

关键词： Sparse Fast Fourier Transform Sparsity Adaptive tuning FFTW

来源：评论

学校读者我要写书评

暂无评论

Registration of Under-Sampled Images via Higher Resolution Spectrum Restoration

Registration of Under-Sampled Images via Higher Resolution S...

引用

IEEE Visual Communications and Image Processing (VCIP) Conference

作者： Song, Qiang Xiong, Ruiqin Zhang, Xinfeng Ma, Siwci Gao, Wen Peking Univ Inst Digital Media Beijing 100871 Peoples R China Nanyang Technol Univ Rapid Rich Object Search Lab Singapore Singapore

ISBN: (纸本)9781467373142

High accuracy image registration is critical for the success of multi-frame super-resolution. Conventionally, the shift between images are estimated directly based on the undersampled low-resolution (LR) image data. However, the high-frequency of LR data is unreliable due to the aliasing effect of sub-sampling, which will deteriorate the accuracy of registration. This paper proposes to resolve the aliasing by converting the LR images to high-resolution (HR) domain and then perform registration on the restored HR spectrum. To recover the HR spectrum for each corresponding LR image, we fuse the LR images into one HR image and project the estimation difference back to the reconstructed HR spectrum iteratively. To address the unequal reliabilities of different restored frequencies, weighted least square is employed to improve the precision of registration. Experimental results show that the proposed method can outperform other existing methods and improve the quality of super-resolution image.

关键词： Image registration super-resolution aliased image spectrum restoration weighted least square

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection 36

Exploiting the Relationship Between Kendall's Rank Correlati...

引用

36th Conference on Neural Information Processing Systems (NeurIPS)

作者： Wang, Fan Kong, Adams Wai-Kin Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Nanyang Technol Univ Rapid Rich Object Search ROSE Lab IGP Singapore Singapore

ISBN: (纸本)9781713871088

Model attributions are important in deep neural networks as they aid practitioners in understanding the models, but recent studies reveal that attributions can be easily perturbed by adding imperceptible noise to the input. The non-differentiable Kendall's rank correlation is a key performance index for attribution protection. In this paper, we first show that the expected Kendall's rank correlation is positively correlated to cosine similarity and then indicate that the direction of attribution is the key to attribution robustness. Based on these findings, we explore the vector space of attribution to explain the shortcomings of attribution defense methods using l(p) norm and propose integrated gradient regularizer (IGR), which maximizes the cosine similarity between natural and perturbed attributions. Our analysis further exposes that IGR encourages neurons with the same activation states for natural samples and the corresponding perturbed samples. Our experiments on different models and datasets confirm our analysis on attribution protection and demonstrate a decent improvement in adversarial robustness.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

ABANDONED object DETECTION USING PIXEL-BASED FINITE STATE MACHINE AND SINGLE SHOT MULTIBOX DETECTOR

ABANDONED OBJECT DETECTION USING PIXEL-BASED FINITE STATE MA...

引用

IEEE International Conference on Multimedia and Expo (IEEE ICME)

作者： Shyam, Devadeep Kot, Alex Athalye, Chinmayee Nanyang Technol Univ Rapid Rich Object Search ROSE Lab Singapore Singapore Coll Engn Pune Elect & Telecommun Engg Pune Maharashtra India

ISBN: (纸本)9781538617373

This paper proposes a robust, scalable framework for automatic detection of abandoned, stationary objects in real time surveillance videos that can pose a security threat. We use the sViBe background modeling method to generate a long-term and a short-term background model to extract foreground objects. Subsequently, a pixel-based FSM detects stationary candidate objects based on the temporal transition of code patterns. In order to classify the stationary candidate objects, we use deep learning method (SSD: Single Shot MultiBox Detector) to detect person and some suspected type of objects which include backpack, handbag. In order to suppress any false alarm, we remove other stationary candidate objects other than the suspected stationary objects. After stationary object detection, we also check if there is no person near by the suspected detected objects for a particular time. We tested the system on four standard public datasets. The results show that our method outperforms the performance of existing results while also being robust to temporary occlusions and illumination changes.

关键词： SSD: Single Shot MultiBox Detector ViBe sViBe GMM SILTP

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：