Horizontal Pyramid Matching for Person Re-Identification

Fu, Yang; Wei, Yunchao; Zhou, Yuqian; Shi, Honghui; Huang, Gao; Wang, Xinchao; Yao, Zhiqiang; Huang, Thomas S.

doi:10.1609/aaai.v33i01.33018295

Cited by 358 publications

(220 citation statements)

References 5 publications

Supporting

Mentioning

219

Contrasting

Order By: Relevance

“…Following the state-of-the-art person re-ID methods [5,6,7,8] we employ the ResNet-50 network [9], pretrained on ImageNet [10], for feature extraction. This ensures that similar results can be expected in different setups.…”

Section: Person Re-id Baselinementioning

confidence: 99%

Deep Joint Source-Channel Coding for Wireless Image Retrieval

Jankowski

Gündüz

Mikolajczyk

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Motivated by surveillance applications with wireless cameras or drones, we consider the problem of image retrieval over a wireless channel. Conventional systems apply lossy compression on query images to reduce the data that must be transmitted over the bandwidth and power limited wireless link. We first note that reconstructing the original image is not needed for retrieval tasks; hence, we introduce a deep neutral network (DNN) based compression scheme targeting the retrieval task. Then, we completely remove the compression step, and propose another DNN-based communication scheme that directly maps the feature vectors to channel inputs. This joint source-channel coding (JSCC) approach not only improves the end-to-end accuracy, but also simplifies and speeds up the encoding operation which is highly beneficial for power and latency constrained IoT applications.

show abstract

Section: Person Re-id Baselinementioning

confidence: 99%

Deep Joint Source-Channel Coding for Wireless Image Retrieval

Jankowski

Gündüz

Mikolajczyk

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…The holistic image-based approaches usually suffer from the overfitting problem [4]. To relieve this problem, partbased approaches [4]- [8], [14] have been proposed to learn discriminative image representations and achieved state-ofthe-art performance. However, due to errors in pedestrian detection, the location of each body part in different images varies.…”

Section: A Person Re-identificationmentioning

confidence: 99%

CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification

Wang

Ding

Maybank

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Part-level representations are essential for robust person re-identification. Due to errors in pedestrian detection, there are usually severe mis-alignment problems for body parts, which degrade the quality of part representations. To handle this problem, we propose a novel model named Convolutional Deformable Part Models (CDPM). CDPM works by decoupling the complex part alignment procedure into two easier steps. First, a vertical alignment step detects each part in the vertical direction with the help of a multi-task learning model. Second, a horizontal refinement step based on self-attention suppresses the background information around each detected body part. Since the two steps are performed orthogonally and sequentially, the difficulty of part alignment is significantly reduced. In the testing stage, CDPM is able to accurately align flexible body parts without the need of any outside information. Extensive experimental results justify the effectiveness of CDPM for part alignment. Most impressively, CDPM achieves state-of-the-art performance on three large-scale datasets: Market-1501, DukeMTMC-ReID, and CUHK03.

show abstract

“…However, failure cases will happen when discriminative body parts are missing. Horizontal Pyramid Matching (HPM) approach is proposed by Fu et al (2018), solving this problem by using partial feature representations at different horizontal pyramid scales and adopting average and max pooling for inter-person variations. For similarity measurement, metric learning approaches are exploited such as cross-view quadratic discriminant analysis (Liao et al, 2015), relative distance comparison optimization (PRDC algorithm) (Zheng et al, 2011), locally-adaptive decision functions (LADF) (Li et al, 2013) and etc.…”

Section: Improvements In Feature Representationmentioning

confidence: 99%

Droplet-Transmitted Infection Risk Ranking Based on Close Proximity Interaction

Guo

Shi

et al. 2020

Front. Neurorobot.

View full text Add to dashboard Cite

We propose an automatic method to identify people who are potentially-infected by droplet-transmitted diseases. This high-risk group of infection was previously identified by conducting large-scale visits/interviews, or manually screening among tons of recorded surveillance videos. Both are time-intensive and most likely to delay the control of communicable diseases like influenza. In this paper, we address this challenge by solving a multi-tasking problem from the captured surveillance videos. This multi-tasking framework aims to model the principle of Close Proximity Interaction and thus infer the infection risk of individuals. The complete workflow includes three essential sub-tasks: (1) person re-identification (REID), to identify the diagnosed patient and infected individuals across different cameras, (2) depth estimation, to provide a spatial knowledge of the captured environment, (3) pose estimation, to evaluate the distance between the diagnosed and potentially-infected subjects. Our method significantly reduces the time and labor costs. We demonstrate the advantages of high accuracy and efficiency of our method. Our method is expected to be effective in accelerating the process of identifying the potentially infected group and ultimately contribute to the well-being of public health.

show abstract

Horizontal Pyramid Matching for Person Re-Identification

Cited by 358 publications

References 5 publications

Deep Joint Source-Channel Coding for Wireless Image Retrieval

Deep Joint Source-Channel Coding for Wireless Image Retrieval

CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification

Droplet-Transmitted Infection Risk Ranking Based on Close Proximity Interaction

Contact Info

Product

Resources

About