Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification

Su, Chi; Yang, Fan; Zhang, Shiliang; Tian, Qi; Davis, Larry S.; Gao, Wen

doi:10.1109/tpami.2017.2679002

Cited by 97 publications

(40 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attribute embedding for domain-transfer learning problem is a new topic and there are only two existing methods. In the experiment, we compare the proposed algorithm against the two existing methods, which are the Joint Semantic and Latent Attribute Modelling (JSLAM) method proposed by Peng et al [19], and the Multi-Task Learning with Low-Rank Attribute Embedding (MTL-LORAE) method proposed by Su et al [21]. The comparison results over the three benchmark data sets are shown in Figure 1.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Cross-Domain Attribute Representation Based on Convolutional Neural Network

Zhang

Liang

et al. 2018

Intelligent Computing Methodologies

View full text Add to dashboard Cite

In the problem of domain transfer learning, we learn a model for the prediction in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while the source domain has sufficient labels. Besides the instances of the data, recently the attributes of data shared across domains are also explored and proven to be very helpful to leverage the information of different domains. In this paper, we propose a novel learning framework for domain-transfer learning based on both instances and attributes. We proposed to embed the attributes of different domains by a shared convolutional neural network (CNN), learn a domain-independent CNN model to represent the information shared by different domains by matching across domains, and a domain-specific CNN model to represent the information of each domain. The concatenation of the three CNN model outputs is used to predict the class label. An iterative algorithm based on gradient descent method is developed to learn the parameters of the model. The experiments over benchmark datasets show the advantage of the proposed model.

show abstract

Section: Resultsmentioning

confidence: 99%

“…But the attributes of the data actually has the nature of stability across the domains. Thus using the attributes of the data is critical for the transfer learning [21,19]. Peng et al [19] proposed to represent the attribute vectors of each data point by using an attribute dictionary.…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain Attribute Representation Based on Convolutional Neural Network

Zhang

Liang

et al. 2018

Intelligent Computing Methodologies

View full text Add to dashboard Cite

show abstract

“…For example, Shi et al [27] present a new semantic attribute learning model which was trained on a fashion photography dataset and adapted to provide a semantic description for person re-identification. Su et al [29] proposed a weakly supervised multi-type attribute learning framework which involved a three-stage training to progressively boost the accuracy of attributes with only a limited number of labeled samples. Schumann et al [26] developed a person re-identification approach which trained an attribute classifier on separate attribute dataset and integrated its responses into the person re-identification model based on CNNs.…”

Section: Related Workmentioning

confidence: 99%

CA ₃ Net

Liu

Zha

Xie

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Person re-identification aims to identify the same pedestrian across non-overlapping camera views. Deep learning techniques have been applied for person re-identification recently, towards learning representation of pedestrian appearance. This paper presents a novel Contextual-Attentional Attribute-Appearance Network (CA 3 Net) for person re-identification. The CA 3 Net simultaneously exploits the complementarity between semantic attributes and visual appearance, the semantic context among attributes, visual attention on attributes as well as spatial dependencies among body parts, leading to discriminative and robust pedestrian representation. Specifically, an attribute network within CA 3 Net is designed with an Attention-LSTM module. It concentrates the network on latent image regions related to each attribute as well as exploits the semantic context among attributes by a LSTM module. An appearance network is developed to learn appearance features from the full body, horizontal and vertical body parts of pedestrians with spatial dependencies among body parts. The CA 3 Net jointly learns the attribute and appearance features in a multi-task learning manner, generating comprehensive representation of pedestrians. Extensive experiments on two challenging benchmarks, i.e., Market-1501 and DukeMTMC-reID datasets, have demonstrated the effectiveness of the proposed approach.

show abstract

“…It demonstrated promising performance in real-world applications including glutamic acid fermentation process modeling, polymer test plant modeling, wine preferences modeling, concrete slump modeling, etc. Su et al [21] proposed MTL with low rank attribute embedding to perform person re-identification on multi-cameras, and demonstrated that it significantly outperformed existing single-task and multi-task approaches. Abadi et al [1] proposed MTL-based regression models to simultaneously learn the relationship between low-level audio-visual features and highlevel valence/arousal ratings from a collection of movie scenes.…”

Section: Introductionmentioning

confidence: 99%

Affect Estimation in 3D Space Using Multi-Task Active Learning for Regression

Huang

2022

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective sample. Particularly, for affect estimation in the 3D space of valence, arousal and dominance, each assessor has to perform the evaluations in three dimensions, which makes the labeling problem even more challenging. Many sophisticated machine learning approaches have been proposed to reduce the data labeling requirement in various other domains, but so far few have considered affective computing. This paper proposes two multi-task active learning for regression approaches, which select the most beneficial samples to label, by considering the three affect primitives simultaneously. Experimental results on the VAM corpus demonstrated that our optimal sample selection approaches can result in better estimation performance than random selection and several traditional single-task active learning approaches. Thus, they can help alleviate the data labeling problem in affective computing, i.e., better estimation performance can be obtained from fewer labeling queries.

show abstract

Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification

Cited by 97 publications

References 59 publications

Cross-Domain Attribute Representation Based on Convolutional Neural Network

Cross-Domain Attribute Representation Based on Convolutional Neural Network

CA ₃ Net

Affect Estimation in 3D Space Using Multi-Task Active Learning for Regression

Contact Info

Product

Resources

About