LEADER 02398nam 2200385 450 001 996560370303316 005 20231129230513.0 035 $a(CKB)28728771000041 035 $a(NjHacI)9928728771000041 035 $a(EXLCZ)9928728771000041 100 $a20231129d2023 uy 0 101 0 $aeng 135 $aur||||||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aProceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval /$fWei Ji, [and four others], SIGMM 210 1$aNew York, NY, USA :$cAssociation for Computing Machinery,$d2023. 215 $a1 online resource (75 pages) 225 0 $aACM Conferences 311 08$a9798400702716 330 $aIt is our great pleasure to welcome you to the 2023 ACM Multimedia Workshop - MMIR 2023. The emergence of multimodal learning offers a feasible way for multimodal IR. Within recent decades with the rapid development of deep learning techniques, the triumph of multimodal learning has been witnessed. Deep multimodal learning has been defined as to use of deep neural techniques to model and learn from multiple sources of data or modalities among others. In the context of IR, deep multimodal learning has shown great potential to improve the performance and application scope of retrieval systems, i.e., by enabling better understanding and processing of the diverse types of data. MMIR'23 workshop can be a good complementarity to place the major focus on multimodal IR. This workshop sets the goal to extend existing work in this direction, by bringing together and facilitating the community of researchers and practitioners. And meanwhile, we aim to encourage an exchange of perspectives and solutions between industry and academia to bridge the gap between academic design guidelines and the best practices in the industry regarding multimodal IR. 606 $aComputer science 606 $aNeural networks 615 0$aComputer science. 615 0$aNeural networks. 676 $a004 700 $aJi$b Wei$01439434 712 02$aSpecial Interest Group on Multimedia Systems, 801 0$bNjHacI 801 1$bNjHacl 906 $aBOOK 912 $a996560370303316 996 $aProceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval$93601612 997 $aUNISA