Attribute-based people search in surveillance environments

Vaquero, Daniel; Feris, Rogério; Tran, Duan; Brown, Lisa M.; Hampapur, Arun; Turk, Matthew

doi:10.1109/wacv.2009.5403131

Cited by 177 publications

(137 citation statements)

References 15 publications

Supporting

Mentioning

136

Contrasting

Unclassified

Order By: Relevance

“…For instance, [5] proposed an attribute-centric approach to help in reporting unusual aspects of known objects, and naming unknown objects; [27] proposed to jointly learn visual attributes, object classes and visual saliency in a unified framework, with consideration of attribute interdependency. Besides object recognition, attribute based approaches are also shown to be effective for video/image search [12,23,26]. In addition, there are works aiming to discover attributes either automatically through the web [2] or semi-automatically with human in the loop [19], and to explore new types of attributes [20].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Weak attributes for large-scale image retrieval

Tsai

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

“…The idea of "attribute" has been advocated in the computer vision community recently, where its effectiveness was demonstrated in various applications such as object recognition [5,13,14,27], and image/video search [12,23,26]. In this paper, we focus on attribute based image retrieval.…”

Section: Introductionmentioning

confidence: 99%

Weak attributes for large-scale image retrieval

Tsai

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

“…Textual queries have also been proposed to retrieve specific individuals based on facial attributes [16]. Moreover, [12] presents a SQL-like language aimed at retrieving and indexing surveillance videos.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Surveillance Video Retrieval Based on Human Action and Appearance

Gerónimo

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Abstract-Forensic video analysis is the offline analysis of video aimed at understanding what happened in a scene in the past. Two of its key tasks are the recognition of specific actions, e.g., walking or fighting, and the search for specific persons, also referred to as re-identification. Although these tasks have traditionally been performed manually in forensic investigations, the current growing number of cameras and recorded video leads to the need for automated analysis. In this paper we propose an unsupervised retrieval system for surveillance videos based on human action and appearance. Given a query window, the system retrieves people performing the same action as the one in the query, the same person performing any action, or the same person performing the same action. We use an adaptive search algorithm that focuses the analysis on relevant frames based on the inter-frame difference of foreground masks. Then, for each analyzed frame, a pedestrian detector is used to extract windows containing each pedestrian in the scene. For each detection, we use optical flow features to represent its action and color features to represent its appearance. These extracted features are used to compute the probability that the detection matches the query according to the specified criterion. The algorithm is fully unsupervised, i.e., no training or constraints on the appearance, actions or number of actions that will appear in the test video are made. The proposed algorithm is tested on a surveillance video with different people performing different actions, providing satisfactory retrieval performance.

show abstract

“…Farhadi et al [7] learn a a richer set of attributes including parts, shape, materials, etc. Vaquero et al [18] introduce a video-based visual surveillance system which allows one to search based on people's fine-grained parts and attributes, e.g. an example could be "show me people with bald head wearing red shirt in the video".…”

Section: Introductionmentioning

confidence: 99%

A Discriminative Latent Model of Object Classes and Attributes

Wang

Mori

2010

Lecture Notes in Computer Science

168

159

View full text Add to dashboard Cite

Abstract. We present a discriminatively trained model for joint modelling of object class labels (e.g. "person", "dog", "chair", etc.) and their visual attributes (e.g. "has head", "furry", "metal", etc.). We treat attributes of an object as latent variables in our model and capture the correlations among attributes using an undirected graphical model built from training data. The advantage of our model is that it allows us to infer object class labels using the information of both the test image itself and its (latent) attributes. Our model unifies object class prediction and attribute prediction in a principled framework. It is also flexible enough to deal with different performance measurements. Our experimental results provide quantitative evidence that attributes can improve object naming.

show abstract

Attribute-based people search in surveillance environments

Cited by 177 publications

References 15 publications

Weak attributes for large-scale image retrieval

Weak attributes for large-scale image retrieval

Unsupervised Surveillance Video Retrieval Based on Human Action and Appearance

A Discriminative Latent Model of Object Classes and Attributes

Contact Info

Product

Resources

About