Context-Aware Hypergraph Modeling for Re-identification and Summarization

Sunderrajan, Santhoshkumar; Manjunath, B.S.

doi:10.1109/tmm.2015.2496139

Cited by 32 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of existing research employs computer-vision algorithms and machine learning techniques to extract and use clothing descriptions in applications including: online person recognition [28], [34]; soft attributes for re-identification [13], [31], [35] along with person detection [11], [12] and tracking [36], [37] or attribute-based people search [11], [13]; detecting and analyzing semantic descriptions (labels) of clothing colors and types to supplement other bodily and soft facial attributes in automatic search and retrieval [15]; and utilizing some clothing attributes like color [38] [39] and style to improve observation and retrieval at a distance in surveillance environments [26]. It will be difficult to analyze clothing in some surveillance images, given poor quality and low resolution, while human-vision analysis offers supportive or alternative solutions [17].…”

Section: B Soft Biometrics and Identitymentioning

confidence: 99%

From Clothing to Identity: Manual and Automatic Soft Biometrics

Jaha

Nixon

2016

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Abstract-Soft biometrics have increasingly attracted research interest and are often considered as major cues for identity, especially in the absence of valid traditional biometrics, as in surveillance. In everyday life, several incidents and forensic scenarios highlight the usefulness and capability of identity information that can be deduced from clothing. Semantic clothing attributes have recently been introduced as a new form of soft biometrics. Although clothing traits can be naturally described and compared by humans for operable and successful use, it is desirable to exploit computer-vision to enrich clothing descriptions with more objective and discriminative information. This allows automatic extraction and semantic description and comparison of visually detectable clothing traits in a manner similar to recognition by eyewitness statements. This study proposes a novel set of soft clothing attributes, described using small groups of high-level semantic labels, and automatically extracted using computer-vision techniques. In this way we can explore the capability of human attributes vis-a-vis those which are inferred automatically by computer-vision. Categorical and comparative soft clothing traits are derived and used for identification/re-identification either to supplement soft body traits or to be used alone. The automatically-and manuallyderived soft clothing biometrics are employed in challenging invariant person retrieval. The experimental results highlight promising potential for use in various applications.

show abstract

Section: B Soft Biometrics and Identitymentioning

confidence: 99%

From Clothing to Identity: Manual and Automatic Soft Biometrics

Jaha

Nixon

2016

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…Graph matching is of great importance in the applications of computer vision and machine learning . This problem is to make recognition of objects by establishing consistent correspondences of the points or line segments between two related graphs that preserves the relationships as much as possible.…”

Section: Introductionmentioning

confidence: 99%

“…Graph matching is of great importance in the applications of computer vision and machine learning. [1][2][3][4][5] This problem is to make recognition of objects by establishing consistent correspondences of the points or line segments between two related graphs that preserves the relationships as much as possible. For solving this problem, many algorithms have been established in the literature; see other works, [6][7][8][9] and the references therein.…”

Section: Introductionmentioning

confidence: 99%

An efficient algorithm for bounded spectral matching with affine constraint

Dou

Chandrasekaran

2019

Numerical Linear Algebra App

View full text Add to dashboard Cite

Summary Graph matching problem appears frequently in the applications of computer vision and machine learning. In this work, based on the spectral matching with affine constraint (SMAC) formulation, we present a new formulation, named bounded SMAC (BSMAC), for the graph matching problem by adding an upper‐bound constraint on the solution norm. We demonstrate the existence of a unique solution with BSMAC, whereas SMAC needs not to have any meaningful solution in general. We develop an effective numerical method to solve the BSMAC formulation as an optimization problem. Numerical experiments are presented to verify feasibility and to show the performance of the proposed numerical method.

show abstract

“…Analysis of realistic human motion is a challenging problem with intra-class and inter-class variations and similarities that require deep appearance and kinetic analysis [31]. Also, the summarization via camera networks enables systems to represent and analyze environments from multipleviews via hypergraphs [33], motion patterns represented as salient motifs [5] and using graphs [45]. These methods, however, are limited to smooth sequential motion in scenes with relatively good illumination and cannot be applied to the ICU.…”

Section: Introductionmentioning

confidence: 99%

A Multiview Multimodal System for Monitoring Patient Sleep

Torres

Fried

Rose

et al. 2018

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

Clinical observations indicate that during critical care at the hospitals, a patient's sleep positioning and motion have a significant effect on recovery rate. Unfortunately, there is no formal medical protocol to record, quantify, and analyze motion of patients. There are very few clinical studies that use manual analysis of sleep poses and motion recordings to support medical benefits of patient positioning and motion monitoring. Manual processes do not scale, are prone to human errors, and put strain on an already taxed healthcare workforce. This study introduces Multimodal, Multiview Motion Analysis and Summarization for healthcare (MASH). MASH is an autonomous system, which addresses these issues by monitoring healthcare environments and enabling the recording and analysis of patient sleep-pose patterns. MASH uses three RGB-D cameras to monitor patients in a medical Intensive Care Unit (ICU) room. The proposed algorithms estimate pose direction at different temporal resolutions and use keyframes to efficiently represent pose transition dynamics. MASH combines deep features computed from the data with a modified version of Hidden Markov Model (HMM) to flexibly model pose duration and summarize patient motion. The performance is evaluated in ideal (BC: Bright and Clear/occlusion-free) and natural (DO: Dark and Occluded) scenarios at two motion resolutions and in two environments: a mock-up and a medical ICU. The usage of deep features is evaluated and their performance compared with engineered features. Experimental results using deep features in DO scenes increases performance from 86.7% to 93.6%, while matching the classification performance of engineered features in BC scenes. The performance of MASH is compared with HMM and C3D. The overall overtime tracing and summarization error rate across all methods increased when transitioning from the mock-up to the the medical ICU data. The proposed keyframe estimation helps achieve a 78% transition classification accuracy.

show abstract

Context-Aware Hypergraph Modeling for Re-identification and Summarization

Cited by 32 publications

References 38 publications

From Clothing to Identity: Manual and Automatic Soft Biometrics

From Clothing to Identity: Manual and Automatic Soft Biometrics

An efficient algorithm for bounded spectral matching with affine constraint

A Multiview Multimodal System for Monitoring Patient Sleep

Contact Info

Product

Resources

About