What and where: A context-based recommendation system for object insertion

作     者：Song-Hai Zhang Zheng-Ping Zhou Bin Liu Xi Dong Peter Hall Song-Hai Zhang;Zheng-Ping Zhou;Bin Liu;Xi Dong;Peter Hall

作者机构：Tsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China Department of Computer Science Media Technology Research CenterUniversity of BathBath BA27AYUK 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2020年第6卷第1期

页      面：79-93页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key Technology R&D Program(Project Number 2016YFB1001402) the National Natural Science Foundation of China(Project Numbers61521002,61772298) Research Grant of Beijing Higher Institution Engineering Research Center Tsinghua–Tencent Joint Laboratory for Internet Innovation Technology 

主　　题：object recommendation bounding box prediction image composition object-level context 

摘      要：We propose a novel problem revolving around two tasks:(i)given a scene,recommend objects to insert,and(ii)given an object category,retrieve suitable background scenes.A bounding box for the inserted object is predicted in both tasks,which helps downstream applications such as semiautomated advertising and video *** major challenge lies in the fact that the target object is neither present nor localized in the input,and furthermore,available datasets only provide scenes with existing *** tackle this problem,we build an unsupervised algorithm based on object-level contexts,which explicitly models the joint probability distribution of object categories and bounding boxes using a Gaussian mixture *** on our own annotated test set demonstrate that our system outperforms existing baselines on all sub-tasks,and does so using a unified *** extensions and applications are suggested.