scispace - formally typeset
Search or ask a question
Proceedings Article•DOI•

A hybrid framework for event detection using multi-modal features

01 Nov 2011-pp 1510-1515
TL;DR: A novel approach for event detection in sports videos by topic based graphical model learning where characteristics features defining various sport events are extracted by contextual grouping of low-level video and audio features using topic modeling.
Abstract: The paper presents a novel approach for event detection in sports videos by topic based graphical model learning. The characteristics features defining various sport events are extracted by contextual grouping of low-level video and audio features using topic modeling. Event detection is performed by learning the structure of context based distribution of characteristic features by CRF based graphical model. Experimental evaluation of the proposed concept is presented on recorded video of Handball and Soccer game.
Citations
More filters
Journal Article•DOI•
TL;DR: This paper proposed an unsupervised approach to extract semantic events from sports webcast text, which extracts significant text events, which can be used for further video indexing and summarization and provides a hierarchical searching scheme for text event retrieval.
Abstract: Semantic event extraction is helpful for video annotation and retrieval. For sports video, most previous works detect events by video content itself. Some useful external knowledge has been researched recently. In this paper, we proposed an unsupervised approach to extract semantic events from sports webcast text. First, unrelated words in the descriptions of webcast text are filtered out, and then the filtered descriptions are clustered into significant event categories. Finally, the keywords for each event category are extracted. According to our experimental results, the proposed approach actually extracts significant text events, which can be used for further video indexing and summarization. Furthermore, we also provide a hierarchical searching scheme for text event retrieval.

20 citations

Proceedings Article•DOI•
01 Oct 2014
TL;DR: A novel framework to tackle challenges of basketball video analysis, where a semantic event extractor is presented to extract semantic events from frames with scoreboard and a slow motion replay Extractor is proposed to extract replays from frames without scoreboard.
Abstract: Semantic event and slow motion replay extraction for sports videos have become hot research topics. Most researches analyze every video frame; however, semantic events only appear in frames with scoreboard, whereas replays only appear in frames without scoreboard. Extracting events and replays from unrelated frames causes defects and leads to degradation of performance. In this paper, a novel framework is proposed to tackle challenges of basketball video analysis. In the framework, a scoreboard detector is first provided to divide video frames to two classes, with/without scoreboard. Then, a semantic event extractor is presented to extract semantic events from frames with scoreboard and a slow motion replay extractor is proposed to extract replays from frames without scoreboard. Experimental results show that the proposed framework is practicable for basketball videos. It is expected that the proposed framework can be extended to other sports.

12 citations

Journal Article•DOI•
TL;DR: A Latent Dirichlet Allocation (LDA) based Group Topic-Author model is proposed for efficient discovery of social astroturfing groups within the tourism domain and an algorithm named Astroturfinger Group Topic Detection (AGTD) is defined for the implementation of the proposed model.
Abstract: Astroturfing is a phenomenon in which sponsors of fake messages or reviews are masked because their intentions are not genuine. Astroturfing reviews are intentionally made to influence people to take decisions in favour of or against a target service or product or organization. The tourism sector being one of the sectors that is flourishing and witnessing unprecedented growth is affected by the activities of astroturfers. Astroturfing reviews can cause many problems to tourists who make decisions based on available online reviews. However, authentic and genuine reviews help people make informed decisions. In this paper a Latent Dirichlet Allocation (LDA) based Group Topic-Author model is proposed for efficient discovery of social astroturfing groups within the tourism domain. An algorithm named Astroturfing Group Topic Detection (AGTD) is defined for the implementation of the proposed model. The experimental results of this study revealed the utility of the proposed system for the discovery of social astroturfing groups within the tourism domain.

3 citations


Cites background from "A hybrid framework for event detect..."

  • ...Hassan et al. (Hassan et al., 2011) exploited multi-modal features for event detection from multimedia content....

    [...]

Proceedings Article•DOI•
01 Oct 2015
TL;DR: An approach of webcast event clustering for sport video event annotation is proposed using one of unsupervised learning algorithms, called pLSA (probabilistic latent semantic analysis), to classify event types.
Abstract: Event detection using webcast text is an important function for providing event based video segmenting services of sport videos. In this paper, an approach of webcast event clustering for sport video event annotation is proposed. In our approach, one of unsupervised learning algorithms, called pLSA (probabilistic latent semantic analysis), is used to classify event types. To decide an appropriate number of event types, lexical pattern analysis is used. By the experimental results, it is observed that our approach could be used to extract event keywords from the basketball webcast texts.

3 citations


Cites background from "A hybrid framework for event detect..."

  • ...Most of proposed approaches use video contents by analyzing low level features (.e.g. color, motion) to automatically extract events[1], [2]....

    [...]

Book Chapter•DOI•
29 Jan 2021
TL;DR: This paper provides key points about feature representations across different modalities, classification techniques for event detection in user-generated videos using multiple modalities.
Abstract: The aim of event detection is to identify interested events in a user-generated content using multiple modalities automatically However, it is a challenging task particularly when videos are captured in a restricted environment by nonprofessionals Such videos suffer from poor quality, deprived lighting, blurring, complex camera motion chaotic background clutter, and obstructions However, with the rise of social media, there is rising popularity of user-generated videos on the Web day-by-day Each minute, 300 hours of user-generated video are uploaded on you tube due to which people find difficult to search the appropriate content among a large number of videos Therefore, solutions to this problem are in great demands In this paper, we study existing technologies for event detection in user-generated videos using multiple modalities This paper provides key points about feature representations across different modalities, classification techniques

1 citations

References
More filters
Journal Article•DOI•
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Abstract: We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.

30,570 citations


"A hybrid framework for event detect..." refers background in this paper

  • ...LDA is defined as generative probabilistic model for collection of documents [2]....

    [...]

Proceedings Article•
03 Jan 2001
TL;DR: This paper proposed a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI).
Abstract: We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.

25,546 citations

Proceedings Article•DOI•
20 Sep 1999
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Abstract: An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.

16,989 citations


"A hybrid framework for event detect..." refers background in this paper

  • ...Based on the analogy between terms in text documents and local descriptors in images, the bag-of-features as extension of bag-of-words has been extensively applied for image analysis [11][5][16]....

    [...]

Proceedings Article•
28 Jun 2001
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Abstract: We present conditional random fields , a framework for building probabilistic models to segment and label sequence data. Conditional random fields offer several advantages over hidden Markov models and stochastic grammars for such tasks, including the ability to relax strong independence assumptions made in those models. Conditional random fields also avoid a fundamental limitation of maximum entropy Markov models (MEMMs) and other discriminative Markov models based on directed graphical models, which can be biased towards states with few successor states. We present iterative parameter estimation algorithms for conditional random fields and compare the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.

13,190 citations


"A hybrid framework for event detect..." refers methods in this paper

  • ...We apply CRF based probabilistic graphical model for modeling the sequential information [7]....

    [...]