Christian X. Ries, Fabian Richter, Stefan Romberg, R. Lienhart
{"title":"Automatic object annotation from weakly labeled data with latent structured SVM","authors":"Christian X. Ries, Fabian Richter, Stefan Romberg, R. Lienhart","doi":"10.1109/CBMI.2014.6849838","DOIUrl":null,"url":null,"abstract":"In this paper we present an approach to automatic object annotation. We are given a set of positive images which all contain a certain object and our goal is to automatically determine the position of said object in each image. Our approach first applies a heuristic to identify initial bounding boxes based on color and gradient features. This heuristic is based on image and feature statistics. Then, the initial boxes are refined by a latent structured SVM training algorithm which is based on the CCCP training algorithm. We show that our approach outperforms previous work on multiple datasets.","PeriodicalId":103056,"journal":{"name":"2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CBMI.2014.6849838","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
In this paper we present an approach to automatic object annotation. We are given a set of positive images which all contain a certain object and our goal is to automatically determine the position of said object in each image. Our approach first applies a heuristic to identify initial bounding boxes based on color and gradient features. This heuristic is based on image and feature statistics. Then, the initial boxes are refined by a latent structured SVM training algorithm which is based on the CCCP training algorithm. We show that our approach outperforms previous work on multiple datasets.