Situated Models of Meaning for Sports Video Retrieval
Michael Fleischman,Deb Roy +1 more
- pp 37-40
Reads0
Chats0
TLDR
A method is proposed that uses data mining to discover temporal patterns in video, and pair these patterns with associated closed captioning text that is used to train a situated model of meaning that significantly improves video retrieval performance.Abstract:
Situated models of meaning ground words in the non-linguistic context, or situation, to which they refer. Applying such models to sports video retrieval requires learning appropriate representations for complex events. We propose a method that uses data mining to discover temporal patterns in video, and pair these patterns with associated closed captioning text. This paired corpus is used to train a situated model of meaning that significantly improves video retrieval performance.read more
Citations
More filters
Proceedings ArticleDOI
Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos
TL;DR: An Integer Programming framework for action recognition and storyline extraction using the storyline model and visual groundings learned from training data is formulated.
Proceedings ArticleDOI
Learning to sportscast: a test of grounded language acquisition
David L. Chen,Raymond J. Mooney +1 more
TL;DR: A novel commentator system that learns language from sportscasts of simulated soccer games and uses a novel algorithm, Iterative Generation Strategy Learning (IGSL), for deciding which events to comment on.
Patent
Generating audience response metrics and ratings from social interest in time-based media
TL;DR: In this paper, social media content items are mapped to relevant time-based media events and used as the basis for calculating metrics based upon the mappings, and ratings of the time based media there from.
Patent
Estimating social interest in time-based media
Michael Fleischman,Deb Roy +1 more
TL;DR: In this paper, social interest in time-based media (e.g., video and audio streams and recordings) segments is estimated through a process of data ingestion and integration, such as particular plays in a sporting event, scenes in a television show, or advertisements in an advertising block.
Journal ArticleDOI
Event Mining in Multimedia Streams
TL;DR: A survey on the problems and solutions in event mining, approached from three aspects: event description, event-modeling components, and current event mining systems.
References
More filters
Journal Article
The mathematics of statistical machine translation: parameter estimation
TL;DR: The authors describe a series of five statistical models of the translation process and give algorithms for estimating the parameters of these models given a set of pairs of sentences that are translations of one another.
Journal ArticleDOI
A language modeling approach to information retrieval
Jay Ponte,W. Bruce Croft +1 more
TL;DR: It will be shown that probabilistic methods can be used to predict topic changes in the context of the task of new event detection and provide further proof of concept for the use of language models for retrieval tasks.
Journal ArticleDOI
Matching words and pictures
TL;DR: A new approach for modeling multi-modal data sets, focusing on the specific case of segmented images with associated text, is presented, and a number of models for the joint distribution of image regions and words are developed, including several which explicitly learn the correspondence between regions and Words.
Journal ArticleDOI
Information retrieval as statistical translation
Adam L. Berger,John Lafferty +1 more
TL;DR: A simple, well motivated model of the document-to-query translation process is proposed, and an algorithm for learning the parameters of this model in an unsupervised manner from a collection of documents is described.
Journal ArticleDOI
Video-based event recognition: activity representation and probabilistic recognition methods
TL;DR: A new representation and recognition method for human activities that recognizes multi-agent events by propagating the constraints and likelihood of event threads in a temporal logic network and presents results on real-world data and performance characterization on perturbed data.