Human Re-identification in Crowd Videos Using Personal, Social and Environmental Constraints

Assari, Shayan Modiri; Idrees, Haroon; Shah, Mubarak

doi:10.1007/978-3-319-46475-6_8

Cited by 18 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Employing group/social information could be a promising direction to further improve system's performance. Although some methods [24,4,2] have made efforts towards this direction for person re-id task, we design a novel context learning framework with graph model in person search scenario.…”

Section: Related Workmentioning

confidence: 99%

“…Existing methods [24] typically utilize manual annotations to locate semantic groups, which requires extensive human labor. Other methods [4,2] make use of spatial and temporal cues such as velocity and relative position in the scene, which are considered as social constraints to model group behaviors to help facilitate person re-id. These social force models utilize elaborately designed constraints to simulate social influences in the scene, which usually does not have trivial solutions and is hard to optimize.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Context Graph for Person Search

Yan

Zhang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

184

119

View full text Add to dashboard Cite

Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning Context Graph for Person Search

Yan

Zhang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

184

119

View full text Add to dashboard Cite

show abstract

“…It was collected between February 2018 and June 2019 across an ecological gradient encompassing primary forest, logged forest, cleared forest, and oil palm sites. [107], pedestrian behavior modeling [108], crowd behavior analysis [109,110], human re-identification [111], tracking [112], tracking [113], crowd counting [54,114] Audiomoth dataset: In the Audiomoth dataset, continuous recording of sound was carried out in consecutive 5 minutes sound files, sampled at 16 kHz, resulting in a total of 748 hours of audio. Audiomoths were secured to trees.…”

Section: Sabah Malaysiamentioning

confidence: 99%

Multimedia Datasets for Anomaly Detection: A Review

Kumari¹,

Bedi²,

Saini³

2021

Preprint

View full text Add to dashboard Cite

Audio or video anomaly datasets play a crucial role in automated surveillance. The range of applications expand from outlier object/ situation detection to the detection of lifethreatening events. This research area has been active for more than 1.5 decades, and consequently, more and more datasets dedicated to anomalous actions and object detection have been created. Making use of these public anomaly datasets enable researchers to compare various anomaly detection frameworks with the same input data. This survey aims to address the lack of a comprehensive comparison and analysis of public datasets for audio, video, and audio-visual based anomaly detection. It also assists in selecting the best dataset for bench-marking frameworks. Additionally, we discuss gaps in the existing dataset and future direction insights toward developing multimodal anomaly detection datasets.

show abstract

“…• It bakes query types in the ingestion. Video queries and operators are increasingly rich [15,21,42,56,64]; one operator (e.g., neural networks) may be instantiated with different parameters depending on training data [18]. Running all possible early operators at ingestion is therefore expensive.…”

Section: System Modelmentioning

confidence: 99%

VStore

Xu¹,

Botelho²,

Lin³

2019

Proceedings of the Fourteenth EuroSys Conference 2019

View full text Add to dashboard Cite

We present VStore, a data store for supporting fast, resourceefficient analytics over large archival videos. VStore manages video ingestion, storage, retrieval, and consumption. It controls video formats along the video data path. It is challenged by i) the huge combinatorial space of video format knobs; ii) the complex impacts of these knobs and their high profiling cost; iii) optimizing for multiple resource types. It explores an idea called backward derivation of configuration: in the opposite direction along the video data path, VStore passes the video quantity and quality expected by analytics backward to retrieval, to storage, and to ingestion. In this process, VStore derives an optimal set of video formats, optimizing for different resources in a progressive manner.VStore automatically derives large, complex configurations consisting of more than one hundred knobs over tens of video formats. In response to queries, VStore selects video formats catering to the executed operators and the target accuracy. It streams video data from disks through decoder to operators. It runs queries as fast as 362× of video realtime.

show abstract

Human Re-identification in Crowd Videos Using Personal, Social and Environmental Constraints

Cited by 18 publications

References 49 publications

Learning Context Graph for Person Search

Learning Context Graph for Person Search

Multimedia Datasets for Anomaly Detection: A Review

VStore

Contact Info

Product

Resources

About