Semi-Coupled Dictionary Learning With Relaxation Label Space Transformation for Video-Based Person Re-Identification

Sun, Lingchuan; Jiang, Zhuqing; Song, Hongchao; Lu, Qishuo; Men, Aidong

doi:10.1109/access.2018.2803789

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [24] embedded constraints on linear transformation matrix and proposed a weight learning strategy to learn the relationships between different variables. Sun et al [25] introduced a pair of transformation matrices to capture the intrinsic relationship of the same person under different camera views for video-based person re-ID.…”

Section: B Person Re-id Approachesmentioning

confidence: 99%

Beyond Scalar Neuron: Adopting Vector-Neuron Capsules for Long-Term Person Re-Identification

Huang

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Current person re-identification (re-ID) works mainly focus on the short-term scenario where a person is less likely to change clothes. However, in the long-term re-ID scenario, a person has a great chance to change clothes. A sophisticated re-ID system should take such changes into account. To facilitate the study of long-term re-ID, this paper introduces a large-scale re-ID dataset called "Celeb-reID" to the community. Unlike previous datasets, the same person can change clothes in the proposed Celeb-reID dataset. Images of Celeb-reID are acquired from the Internet using street snap-shots of celebrities. There is a total of 1,052 IDs with 34,186 images making Celeb-reID being the largest long-term re-ID dataset so far. To tackle the challenge of cloth changes, we propose to use vector-neuron (VN) capsules instead of the traditional scalar neurons (SN) to design our network.Compared with SN, one extra-dimensional information in VN can perceive cloth changes of the same person. We introduce a well-designed ReIDCaps network and integrate capsules to deal with the person re-ID task. Soft Embedding Attention (SEA) and Feature Sparse Representation (FSR) mechanisms are adopted in our network for performance boosting.Experiments are conducted on the proposed long-term re-ID dataset and two common short-term re-ID datasets. Comprehensive analyses are given to demonstrate the challenge exposed in our datasets. Experimental results show that our ReIDCaps can outperform existing state-of-the-art methods by a large margin in the long-term scenario. The new dataset and code will be released to facilitate future researches.

show abstract

Section: B Person Re-id Approachesmentioning

confidence: 99%

Beyond Scalar Neuron: Adopting Vector-Neuron Capsules for Long-Term Person Re-Identification

Huang

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…The main property of learned dictionary is that it can approximate input data as a linear combination of a small number of elements from dictionary. It has shown superior performance and been successfully applied to a wide variety of applications in computer vision community, such as image denoising [9]- [11], face recognition [12], [13], image super-resolution [14]- [16], object detection [17], [18], pose estimation [19], person re-identification [20]- [22], and image classification [23]- [30] and etc.…”

Section: Introductionmentioning

confidence: 99%

Learning Category-Specific Sharable and Exemplary Visual Elements for Image Classification

Xie

Song

2020

IEEE Access

View full text Add to dashboard Cite

This paper presents a novel method to determine the discriminative image representation via visual dictionary learning framework for image classification task. Visual dictionary learning has the capacity to represent input image using an over-complete element set. Sparsity restrains distractors and prevents overfitting. The two main characteristics benefit the classification solution. However, one shortcoming of existing dictionary learning is that it neglects to exploit the potential correlations across visual elements, especially from the category-specific feature space. To address this problem, we first propose to learn multiple discriminative category-specific dictionaries (DCSD) from all categories. The DCSD can explore the visual elements from each category in terms of sharable property. For this reason, these learned category-specific visual elements encourage image features from the same class to have the similar feature representations. In addition, exemplary data reflect the main characteristic of whole dataset and can improve the performance of algorithm that employs them. Therefore, we further propose a representative pattern dictionary (RPD) model to discover the exemplary visual elements for promoting the discriminative capability of feature representation. These exemplary visual elements are essentially a subset of over-complete visual elements and can represent the whole sample data effectively. Finally, we design a novel strategy that integrates the merits of object proposals and deep features jointly to strengthen the semantic information of image-level feature. Experimental results on benchmark datasets demonstrate the effectiveness of our method, which is shown to be superior to the recently competing dictionary learning and deep learning based image classification approaches. INDEX TERMS Dictionary learning, deep feature, group sparsity.

show abstract

“…For instance, in video surveillance, multiple high-resolution cameras are necessary to be placed at different locations. They work together to identify [1], [2], re-identity [3], [4], and track the moving target [5], [6], making the later high-level analyses based on the moving target (e.g., behavior or even potential intention) more feasible. In emotional computation, high-resolution cameras need to be utilized to capture both obvious and fine…”

Section: Introductionmentioning

confidence: 99%

Video-Based Abnormal Driving Behavior Detection via Deep Learning Fusions

et al. 2019

View full text Add to dashboard Cite

Video-based abnormal driving behavior detection is becoming more and more popular for the time being, as it is highly important in ensuring safeties of drivers and passengers in the vehicle, and it is an essential step in realizing automatic driving at the current stage. Thanks to recent developments in deep learning techniques, this challenging detection task can be largely facilitated via the prominent generalization capability of sophisticated deep learning models as well as large volumes of video clips which are indispensable for thoroughly training these data-driven deep learning models. In this paper, deep learning fusion techniques are emphasized, and three novel deep learning-based fusion models inspired by the recently proposed and popular densely connected convolutional network (DenseNet) are introduced, to fulfill the video-based abnormal driving behavior detection task for the first time. These three new deep learning-based fusion models are named as the wide group densely (WGD) network, the wide group residual densely (WGRD) network, and the alternative wide group residual densely (AWGRD) network, respectively. Technically, WGD takes important issues of deep learning models, i.e., the depth, the width and the cardinality, into consideration when designing its model structure based on DenseNet. For the WGRD and AWGRD, they are more sophisticated as the important idea of residual networks with superpositions of previous layers is incorporated. The extensive experiments are conducted to verify the effectiveness of three new models. Their superiority has been suggested based on rigorous comparisons towards several popular deep learning models in this video-based abnormal driving behavior detection study.INDEX TERMS Artificial intelligence, digital images, vehicle driving, abnormal driving detection, densely connected convolutional networks, deep learning.

show abstract

Semi-Coupled Dictionary Learning With Relaxation Label Space Transformation for Video-Based Person Re-Identification

Cited by 12 publications

References 34 publications

Beyond Scalar Neuron: Adopting Vector-Neuron Capsules for Long-Term Person Re-Identification

Beyond Scalar Neuron: Adopting Vector-Neuron Capsules for Long-Term Person Re-Identification

Learning Category-Specific Sharable and Exemplary Visual Elements for Image Classification

Video-Based Abnormal Driving Behavior Detection via Deep Learning Fusions

Contact Info

Product

Resources

About