Video event recognition using concept attributes

Liu, Jingen; Yu, Qian; Javed, Omar; Ali, Saad; Tamrakar, Amir; Divakaran, Ajay; Cheng, Hui; Sawhney, Harpreet

doi:10.1109/wacv.2013.6475038

Cited by 80 publications

(73 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first phase is video analysis and in this phase we adopted a Concept-Based Event Recognition (CBER) approach to video event classification similar to Ref. 5. We modeled events in a semantic space consisting of concepts related to actions, scenes and objects.…”

Section: Proposed Solutionmentioning

confidence: 99%

“…However, unlike Ref. 5 we used Spatio-Temporal Interest Points Chain (STIPC) for detection of action concepts and chisquare ( 2 χ ) radial basis function (RBF) kernel for SVM learning. In the second phase which is crime prediction, we developed a neuro-fuzzy inference system for computing crime imminence levels across our simulated study area.…”

Section: Proposed Solutionmentioning

confidence: 99%

“…To build the events models we used a combination of bag of concepts (BoC) and cooccurrence of concepts (CoC) methods. 5 Having obtained the event models in semantic concept space we can tell if a query video belongs to an event by computing their semantic similarity in the concept space. For instance if we take 1 2 ( , ,..., ) y y y y n C c c c = as the location of an event in the concept space then given a query video x , we can compute its event label y * as:…”

Section: Event Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Crime Hotspot Detection and Monitoring Using Video Based Event Modeling and Mapping Techniques*

Zou¹,

Mohammed²,

Zhu³

et al. 2017

IJCIS

View full text Add to dashboard Cite

This paper presents a new approach to crime hotspot detection and monitoring. The approach consists of three phases' namely: video analysis, crime prediction and crime mapping. In video analysis, crime indicator events are modelled using statistical distribution of semantic concepts. In crime prediction, a neuro-fuzzy method is used to model indicator events. In crime mapping, kernel density estimation is used to detect crime hotspots. This approach is tested in a simulated platform using violent scene detection (VSD) 2014 dataset.

show abstract

Section: Proposed Solutionmentioning

confidence: 99%

Section: Proposed Solutionmentioning

confidence: 99%

Section: Event Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Crime Hotspot Detection and Monitoring Using Video Based Event Modeling and Mapping Techniques*

Zou¹,

Mohammed²,

Zhu³

et al. 2017

IJCIS

View full text Add to dashboard Cite

show abstract

“…In [4], a multimedia event recounting method is proposed based on detected concepts in order to build discriminative event models using a SVM. Similar work is carried out in [5] aiming at video event classification using semantic concept attributes of different categories like action, scene, object, etc. [6] employed an intermediate representation of semantic model vectors trained from SVMs as a basis for detecting complex events, and revealed that this representation outperforms -and is complementary to -other low-level visual descriptors for event modeling.…”

Section: Introductionmentioning

confidence: 99%

What are the Limits to Time Series Based Recognition of Semantic Concepts?

Wang

Sun

Smeaton

2016

MultiMedia Modeling

View full text Add to dashboard Cite

Abstract. Most concept recognition in visual multimedia is based on relatively simple concepts, things which are present in the image or video. These usually correspond to objects which can be identified in images or individual frames. Yet there is also a need to recognise semantic concepts which have a temporal aspect corresponding to activities or complex events. These require some form of time series for recognition and also require some individual concepts to be detected so as to utilise their time-varying features, such as co-occurrence and re-occurrence patterns. While results are reported in the literature of using concept detections which are relatively specific and static, there are research questions which remain unanswered. What concept detection accuracies are satisfactory for time series recognition? Can recognition methods perform equally well across various concept detection performances? What affecting factors need to be taken into account when building concept-based high-level event/activity recognitions? In this paper, we conducted experiments to investigate these questions. Results show that though improving concept detection accuracies can enhance the recognition of time series based concepts, they do not need to be very accurate in order to characterize the dynamic evolution of time series if appropriate methods are used. Experimental results also point out the importance of concept selection for time series recognition, which is usually ignored in the current literature.

show abstract

“…Whilst the local neighbourhood structure is preserved by consider- Human language is the predominant means of communication. The utilisation of human language models in computer vision problems such as scene understanding [80], image or video description [58] could help in transferring knowledge acquired by human experts for solving these problems.…”

Section: Unsupervised Automatic Attribute Discovery Methods Via Multi-mentioning

confidence: 99%

Discovering visual attributes from image and video data

Liu¹

View full text Add to dashboard Cite

Visual attributes have recently attracted great attention from the computer vision community.Their advantages include being: (1) shared across classes, (2) human understandable, and (3) machine computable. Despite these positives, the attribute features in current works are not discriminative enough to be considered as strong features for traditional classification tasks or novel applications. This problem hinders their broad usage. There are several works that primarily focus on increasing the discriminative power of visual attributes. Unfortunately, in most cases, the feature descriptors become hard to understand (i.e., not meaningful); thus, reducing these attribute features into being merely traditional low-level image/video feature descriptors. Furthermore, the discriminative power property and meaningful property are not independent. Some discriminative attributes could be meaningful and vice-versa. For example, the attribute "has hooves" is discriminative for distinguishing between dogs and sheep but the attribute "has four legs" is not. On the other hand, there is significant attention being given to the development of automatic attribute discovery approaches. These approaches focus on automatically discovering potentially meaningful attributes from data without the need for manual labelling. Although it is suggested that the discovered attributes are quite discriminative and meaningful, it is not entirely clear if they are truly meaningful. Quantitative and automatic evaluation methods to determine attribute meaningfulness are desirable in this case, since manual examination is both tedious and time-consuming. Research on this topic can start to shed light on how to automatically and effectively discover meaningful visual attributes without the huge cost of manual labelling.The following research directions have not previously been extensively explored: (1) current works fail to address the problem of finding discriminative and meaningful attributes without involving human effort, and (2) there is no existing way to measure the meaning of discriminative attributes without involving human labelling effort. To that end, this research aims to devise visual attributebased methods for traditional classification tasks and novel applications, including the attribute meaningfulness measurement, by dealing with these two shortcomings. In particular, this thesis addresses the following aspects: (1) automatic discovery of discriminative attributes from a set of meaningful attributes applied to zero-shot learning problems; (2) discovery of meaningful attributes by exploring ways to automatically quantify attribute meaningfulness; the proposed techniques are applied and tested on video keyword generation for video surveillance data, and (3) discovering meaningful and discriminative attributes in fully unsupervised scenarios via multi-graph clustering techniques. The main contribution of this thesis lies in the proposition of the method quantitatively evaluating the meaningfulness of automatic discovered attr...

show abstract

Video event recognition using concept attributes

Cited by 80 publications

References 32 publications

Crime Hotspot Detection and Monitoring Using Video Based Event Modeling and Mapping Techniques*

Crime Hotspot Detection and Monitoring Using Video Based Event Modeling and Mapping Techniques*

What are the Limits to Time Series Based Recognition of Semantic Concepts?

Discovering visual attributes from image and video data

Contact Info

Product

Resources

About