Two Stream Deep CNN-RNN Attentive Pooling Architecture for Video-Based Person Re-identification

Ansar, Wajeeha; Fraz, Muhammad Moazam; Shahzad, Muhammad; Gohar, I.; Javed, Sajid; Jung, Soon Ki

doi:10.1007/978-3-030-13469-3_76

Cited by 8 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…You et al [34] extracted and combined both spacetime-and appearance-based features for solving the video-based Re-id challenges with reasonable accuracy. Ansar et al [35] presented a two stream deep learning technique that fuses temporal and spatial information for video person re-identification removing meaningless frames via attentive pooling. The Re-id methods that are based on only appearance face the challenge of rapidly changing appearance.…”

Section: Literature Reviewmentioning

confidence: 99%

Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns

Gohar

Riaz

Shahzad

et al. 2020

Sensors

View full text Add to dashboard Cite

Person re-identification (re-ID) is among the essential components that play an integral role in constituting an automated surveillance environment. Majorly, the problem is tackled using data acquired from vision sensors using appearance-based features, which are strongly dependent on visual cues such as color, texture, etc., consequently limiting the precise re-identification of an individual. To overcome such strong dependence on visual features, many researchers have tackled the re-identification problem using human gait, which is believed to be unique and provide a distinctive biometric signature that is particularly suitable for re-ID in uncontrolled environments. However, image-based gait analysis often fails to extract quality measurements of an individual’s motion patterns owing to problems related to variations in viewpoint, illumination (daylight), clothing, worn accessories, etc. To this end, in contrast to relying on image-based motion measurement, this paper demonstrates the potential to re-identify an individual using inertial measurements units (IMU) based on two common sensors, namely gyroscope and accelerometer. The experiment was carried out over data acquired using smartphones and wearable IMUs from a total of 86 randomly selected individuals including 49 males and 37 females between the ages of 17 and 72 years. The data signals were first segmented into single steps and strides, which were separately fed to train a sequential deep recurrent neural network to capture implicit arbitrary long-term temporal dependencies. The experimental setup was devised in a fashion to train the network on all the subjects using data related to half of the step and stride sequences only while the inference was performed on the remaining half for the purpose of re-identification. The obtained experimental results demonstrate the potential to reliably and accurately re-identify an individual based on one’s inertial sensor data.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns

Gohar

Riaz

Shahzad

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Generally, person re-identification is handled as a classification or retrieval task ( Ansar et al, 2018 ; Batool et al, 2018 ). Each person with a unique id makes a separate class and all images of that person captured by different cameras belong to the same class.…”

Section: Introductionmentioning

confidence: 99%

Stochastic attentions and context learning for person re-identification

Perwaiz

Fraz

Shahzad

2021

PeerJ Computer Science

View full text Add to dashboard Cite

The discriminative parts of people’s appearance play a significant role in their re-identification across non overlapping camera views. However, just focusing on the discriminative or attention regions without catering the contextual information does not always help. It is more important to learn the attention with reference to their spatial locations in context of the whole image. Current person re-identification (re-id) approaches either use separate modules or classifiers to learn both of these; the attention and its context, resulting in highly expensive person re-id solutions. In this work, instead of handling attentions and the context separately, we employ a unified attention and context mapping (ACM) block within the convolutional layers of network, without any additional computational resources overhead. The ACM block captures the attention regions as well as the relevant contextual information in a stochastic manner and enriches the final person representations for robust person re-identification. We evaluate the proposed method on 04 public benchmarks of person re-identification i.e., Market1501, DukeMTMC-Reid, CUHK03 and MSMT17 and find that the ACM block consistently improves the performance of person re-identification over the baseline networks.

show abstract

Per-former: rethinking person re-identification using transformer augmented with self-attention and contextual mapping

2022

View full text Add to dashboard Cite

Two Stream Deep CNN-RNN Attentive Pooling Architecture for Video-Based Person Re-identification

Cited by 8 publications

References 17 publications

Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns

Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns

Stochastic attentions and context learning for person re-identification

Per-former: rethinking person re-identification using transformer augmented with self-attention and contextual mapping

Contact Info

Product

Resources

About