Discovering Thematic Objects in Image Collections and Videos. Yuan, J., Zhao, G., Fu, Y., Li, Z., Katsaggelos, A. K., Wu, Y., Junsong Yuan, Gangqiang Zhao, Yun Fu, Zhu Li, Katsaggelos, A. K., & Ying Wu IEEE Transactions on Image Processing, 21(4):2207–2219, apr, 2012. ![Discovering Thematic Objects in Image Collections and Videos [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Given a collection of images or a short video sequence, we define a thematic object as the key object that frequently appears and is the representative of the visual contents. Successful discovery of the thematic object is helpful for object search and tagging, video summarization and understanding, etc. However, this task is challenging because 1) there lacks a priori knowledge of the thematic objects, such as their shapes, scales, locations, and times of re-occurrences, and 2) the thematic object of interest can be under severe variations in appearances due to viewpoint and lighting condition changes, scale variations, etc. Instead of using a top-down generative model to discover thematic visual patterns, we propose a novel bottom-up approach to gradually prune uncommon local visual primitives and recover the thematic objects. A multilayer candidate pruning procedure is designed to accelerate the image data mining process. Our solution can efficiently locate thematic objects of various sizes and can tolerate large appearance variations of the same thematic object. Experiments on challenging image and video data sets and comparisons with existing methods validate the effectiveness of our method. © 2011 IEEE.
@article{Yuan2012,
abstract = {Given a collection of images or a short video sequence, we define a thematic object as the key object that frequently appears and is the representative of the visual contents. Successful discovery of the thematic object is helpful for object search and tagging, video summarization and understanding, etc. However, this task is challenging because 1) there lacks a priori knowledge of the thematic objects, such as their shapes, scales, locations, and times of re-occurrences, and 2) the thematic object of interest can be under severe variations in appearances due to viewpoint and lighting condition changes, scale variations, etc. Instead of using a top-down generative model to discover thematic visual patterns, we propose a novel bottom-up approach to gradually prune uncommon local visual primitives and recover the thematic objects. A multilayer candidate pruning procedure is designed to accelerate the image data mining process. Our solution can efficiently locate thematic objects of various sizes and can tolerate large appearance variations of the same thematic object. Experiments on challenging image and video data sets and comparisons with existing methods validate the effectiveness of our method. {\textcopyright} 2011 IEEE.},
author = {Yuan, Junsong and Zhao, Gangqiang and Fu, Yun and Li, Zhu and Katsaggelos, Aggelos K. and Wu, Ying and {Junsong Yuan} and {Gangqiang Zhao} and {Yun Fu} and {Zhu Li} and Katsaggelos, Aggelos K. and {Ying Wu}},
doi = {10.1109/TIP.2011.2181952},
issn = {1057-7149},
journal = {IEEE Transactions on Image Processing},
keywords = {Image data mining,thematic object discovery},
month = {apr},
number = {4},
pages = {2207--2219},
pmid = {22207639},
title = {{Discovering Thematic Objects in Image Collections and Videos}},
url = {http://ieeexplore.ieee.org/document/6112717/},
volume = {21},
year = {2012}
}
Downloads: 0
{"_id":"pn2fc282QTnQhHa4k","bibbaseid":"yuan-zhao-fu-li-katsaggelos-wu-junsongyuan-gangqiangzhao-etal-discoveringthematicobjectsinimagecollectionsandvideos-2012","author_short":["Yuan, J.","Zhao, G.","Fu, Y.","Li, Z.","Katsaggelos, A. K.","Wu, Y.","Junsong Yuan","Gangqiang Zhao","Yun Fu","Zhu Li","Katsaggelos, A. K.","Ying Wu"],"bibdata":{"bibtype":"article","type":"article","abstract":"Given a collection of images or a short video sequence, we define a thematic object as the key object that frequently appears and is the representative of the visual contents. Successful discovery of the thematic object is helpful for object search and tagging, video summarization and understanding, etc. However, this task is challenging because 1) there lacks a priori knowledge of the thematic objects, such as their shapes, scales, locations, and times of re-occurrences, and 2) the thematic object of interest can be under severe variations in appearances due to viewpoint and lighting condition changes, scale variations, etc. Instead of using a top-down generative model to discover thematic visual patterns, we propose a novel bottom-up approach to gradually prune uncommon local visual primitives and recover the thematic objects. A multilayer candidate pruning procedure is designed to accelerate the image data mining process. Our solution can efficiently locate thematic objects of various sizes and can tolerate large appearance variations of the same thematic object. Experiments on challenging image and video data sets and comparisons with existing methods validate the effectiveness of our method. © 2011 IEEE.","author":[{"propositions":[],"lastnames":["Yuan"],"firstnames":["Junsong"],"suffixes":[]},{"propositions":[],"lastnames":["Zhao"],"firstnames":["Gangqiang"],"suffixes":[]},{"propositions":[],"lastnames":["Fu"],"firstnames":["Yun"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Zhu"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Ying"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Junsong Yuan"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Gangqiang Zhao"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Yun Fu"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Zhu Li"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Ying Wu"],"suffixes":[]}],"doi":"10.1109/TIP.2011.2181952","issn":"1057-7149","journal":"IEEE Transactions on Image Processing","keywords":"Image data mining,thematic object discovery","month":"apr","number":"4","pages":"2207–2219","pmid":"22207639","title":"Discovering Thematic Objects in Image Collections and Videos","url":"http://ieeexplore.ieee.org/document/6112717/","volume":"21","year":"2012","bibtex":"@article{Yuan2012,\nabstract = {Given a collection of images or a short video sequence, we define a thematic object as the key object that frequently appears and is the representative of the visual contents. Successful discovery of the thematic object is helpful for object search and tagging, video summarization and understanding, etc. However, this task is challenging because 1) there lacks a priori knowledge of the thematic objects, such as their shapes, scales, locations, and times of re-occurrences, and 2) the thematic object of interest can be under severe variations in appearances due to viewpoint and lighting condition changes, scale variations, etc. Instead of using a top-down generative model to discover thematic visual patterns, we propose a novel bottom-up approach to gradually prune uncommon local visual primitives and recover the thematic objects. A multilayer candidate pruning procedure is designed to accelerate the image data mining process. Our solution can efficiently locate thematic objects of various sizes and can tolerate large appearance variations of the same thematic object. Experiments on challenging image and video data sets and comparisons with existing methods validate the effectiveness of our method. {\\textcopyright} 2011 IEEE.},\nauthor = {Yuan, Junsong and Zhao, Gangqiang and Fu, Yun and Li, Zhu and Katsaggelos, Aggelos K. and Wu, Ying and {Junsong Yuan} and {Gangqiang Zhao} and {Yun Fu} and {Zhu Li} and Katsaggelos, Aggelos K. and {Ying Wu}},\ndoi = {10.1109/TIP.2011.2181952},\nissn = {1057-7149},\njournal = {IEEE Transactions on Image Processing},\nkeywords = {Image data mining,thematic object discovery},\nmonth = {apr},\nnumber = {4},\npages = {2207--2219},\npmid = {22207639},\ntitle = {{Discovering Thematic Objects in Image Collections and Videos}},\nurl = {http://ieeexplore.ieee.org/document/6112717/},\nvolume = {21},\nyear = {2012}\n}\n","author_short":["Yuan, J.","Zhao, G.","Fu, Y.","Li, Z.","Katsaggelos, A. K.","Wu, Y.","Junsong Yuan","Gangqiang Zhao","Yun Fu","Zhu Li","Katsaggelos, A. K.","Ying Wu"],"key":"Yuan2012","id":"Yuan2012","bibbaseid":"yuan-zhao-fu-li-katsaggelos-wu-junsongyuan-gangqiangzhao-etal-discoveringthematicobjectsinimagecollectionsandvideos-2012","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/6112717/"},"keyword":["Image data mining","thematic object discovery"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["image data mining","thematic object discovery"],"search_terms":["discovering","thematic","objects","image","collections","videos","yuan","zhao","fu","li","katsaggelos","wu","junsong yuan","gangqiang zhao","yun fu","zhu li","katsaggelos","ying wu"],"title":"Discovering Thematic Objects in Image Collections and Videos","year":2012}