Content-Based Attention Ranking Using Visual and Contextual Attention Model for Baseball Videos

Shih, Huang-Chia; Hwang, Jenq‐Neng; Huang, Chung‐Lin

doi:10.1109/tmm.2008.2009682

Cited by 13 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) In the factor ensembles each base classifier models a certain context-independent factor affecting the final classification result, the factors' weights (in the weighted average, voting, or other fusion methods) being adapted to the context in order to increase the accuracy on the target context data [ 52 , 55 , 91 ]. The training datasets can be quite small if the number of these factors is small.…”

Section: Basic Approaches and Examples Of The Lightweight Adaptatimentioning

confidence: 99%

Lightweight Adaptation of Classifiers to Users and Contexts: Trends of the Emerging Domain

Vildjiounaite

Gimel’farb

Kyllönen

et al. 2015

The Scientific World Journal

View full text Add to dashboard Cite

Intelligent computer applications need to adapt their behaviour to contexts and users, but conventional classifier adaptation methods require long data collection and/or training times. Therefore classifier adaptation is often performed as follows: at design time application developers define typical usage contexts and provide reasoning models for each of these contexts, and then at runtime an appropriate model is selected from available ones. Typically, definition of usage contexts and reasoning models heavily relies on domain knowledge. However, in practice many applications are used in so diverse situations that no developer can predict them all and collect for each situation adequate training and test databases. Such applications have to adapt to a new user or unknown context at runtime just from interaction with the user, preferably in fairly lightweight ways, that is, requiring limited user effort to collect training data and limited time of performing the adaptation. This paper analyses adaptation trends in several emerging domains and outlines promising ideas, proposed for making multimodal classifiers user-specific and context-specific without significant user efforts, detailed domain knowledge, and/or complete retraining of the classifiers. Based on this analysis, this paper identifies important application characteristics and presents guidelines to consider these characteristics in adaptation design.

show abstract

Section: Basic Approaches and Examples Of The Lightweight Adaptatimentioning

confidence: 99%

Lightweight Adaptation of Classifiers to Users and Contexts: Trends of the Emerging Domain

Vildjiounaite

Gimel’farb

Kyllönen

et al. 2015

The Scientific World Journal

View full text Add to dashboard Cite

show abstract

“…Let M m v ðf i Þ indicate the visual attention model of frame f i with feature map m. We can formulate this process as the average attention contributed by all objects involved, weighted by a Gaussian weighting function. 15 The camera motion attention model adjusts the visual attention, frame by frame, and is emphasized or degraded by the value M cm , which is powered by the switch function SW cm .…”

Section: Ieee Multimediamentioning

confidence: 99%

“…We derive AR v by transforming visual attention models to a human attention rank. 15 Specifically, we can acquire the visual attention rank of frame f k by the weighted sum of M different types of visual attention models with weights l m W m¼1$M , which are initialized with equal probabilities. Finally, we normalize the rank score by the sum of the visual attention models of all frames f 0 belonging to the same shot S i .…”

Section: Interactive Attention Rankingmentioning

confidence: 99%

An Interactive Attention- Ranking System for Video Search

2009

Self Cite

View full text Add to dashboard Cite

“…T HE video broadcasting has been highly prevalent application that becomes increasingly important for many usages such as video search, management, and transmission [1]- [3]. The key-frame determination is the one of the most effective mechanisms to represent the whole video using a few frames.…”

Section: Introductionmentioning

confidence: 99%

A Novel Attention-Based Key-Frame Determination Method

Shih

2013

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

This paper presents a novel key-frame detection method that combines the visual saliency-based attention features with the contextual game status information for sports videos. Two critical issues of the attention-based video content analysis are addressed: 1) the visual attention characteristics when a user is watching a video clip and 2) extracting the degree of excitement about the on-going game status. First, the objectoriented visual attention map and the algorithm of determining the contextual attention are presented. The procedure of the contextual inference is used to simulate how the game status attracts the viewers. Second, a fusion methodology of visual and contextual attention analysis based on the characteristics of human excitement is introduced. In addition, the amount of key-frames is determined by using the contextual attention score, while the key-frame determination depends on integrating all the visual attention scores. In experimental results, it demonstrates the robustness of the proposed system for basketball and baseball programs.Index Terms-Adaptive key-frame rate, attention modeling, content-based analysis, contextual attention, key-frame determination, visual attention model.

show abstract

Content-Based Attention Ranking Using Visual and Contextual Attention Model for Baseball Videos

Cited by 13 publications

References 41 publications

Lightweight Adaptation of Classifiers to Users and Contexts: Trends of the Emerging Domain

Lightweight Adaptation of Classifiers to Users and Contexts: Trends of the Emerging Domain

An Interactive Attention- Ranking System for Video Search

A Novel Attention-Based Key-Frame Determination Method

Contact Info

Product

Resources

About