{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:09Z","timestamp":1740122889514,"version":"3.37.3"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T00:00:00Z","timestamp":1689033600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T00:00:00Z","timestamp":1689033600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-15779-y","type":"journal-article","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T14:02:03Z","timestamp":1689084123000},"page":"14857-14881","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal query-guided object localization"],"prefix":"10.1007","volume":"83","author":[{"given":"Aditay","family":"Tripathi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajath R","family":"Dani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-9152","authenticated-orcid":false,"given":"Anirban","family":"Chakraborty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,11]]},"reference":[{"key":"15779_CR1","first-page":"24206","volume":"34","author":"H Akbari","year":"2021","unstructured":"Akbari H, Yuan L, Qian R, Chuang W-H, Chang S-F, Cui Y, Gong B (2021) Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text. Proceedings of the Conference on Neural Information Processing Systems (NIPS) 34:24206\u201324221","journal-title":"Proceedings of the Conference on Neural Information Processing Systems (NIPS)"},{"issue":"2","key":"15779_CR2","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L-P (2018) Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 41(2):423\u2013443","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"15779_CR3","doi-asserted-by":"crossref","unstructured":"Bansal A, Sikka K, Sharma G, Chellappa R, Divakaran A (2018) Zero-shot object detection. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 384\u2013400","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"15779_CR4","doi-asserted-by":"crossref","unstructured":"Bhunia AK, Koley S, Khilji AFUR, Sain A, Chowdhury PN, Xiang T, Song Y-Z (2022) Sketching without worrying: Noise-tolerant sketch-based image retrieval. ArXiv arXiv:2203.14817","DOI":"10.1109\/CVPR52688.2022.00107"},{"key":"15779_CR5","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade R-CNN: Delving into high quality object detection. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"issue":"9","key":"15779_CR6","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1016\/S0042-6989(01)00002-5","volume":"41","author":"AJ Calder","year":"2001","unstructured":"Calder AJ, Burton AM, Miller P, Young AW, Akamatsu S (2001) A principal component analysis of facial expressions. Vis Res 41(9):1179\u20131208","journal-title":"Vis Res"},{"key":"15779_CR7","doi-asserted-by":"publisher","first-page":"14053","DOI":"10.4137\/CIN.S14053","volume":"13","author":"Y Cao","year":"2014","unstructured":"Cao Y, Steffey S, He J, Xiao D, Tao C, Chen P, M\u00fcller H (2014) Medical image retrieval: a multimodal approach. Cancer Informat 13:14053","journal-title":"Cancer Informat"},{"key":"15779_CR8","doi-asserted-by":"crossref","unstructured":"Chen Z, Huang S, Tao D (2018) Context refinement for object detection. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 71\u201386","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"15779_CR9","doi-asserted-by":"crossref","unstructured":"Choe J, Shim H (2019) Attention-based dropout layer for weakly supervised object localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 2219\u20132228","DOI":"10.1109\/CVPR.2019.00232"},{"key":"15779_CR10","doi-asserted-by":"crossref","unstructured":"Chowdhury PN, Bhunia AK, Gajjala VR, Sain A, Xiang T, Song Y-Z (2022) Partially does it: Towards scene-level fg-sbir with partial input. ArXiv arXiv:2203.14804","DOI":"10.1109\/CVPR52688.2022.00243"},{"key":"15779_CR11","doi-asserted-by":"crossref","unstructured":"Dang-Nguyen D-T, Boato G, Moschitti A, De\u00a0Natale FG (2012) Supervised models for multimodal image retrieval based on visual, semantic and geographic information. In: Proceedings of the International Workshop on Content-Based Multimedia Indexing (CBMI), pp 1\u20135 IEEE","DOI":"10.1109\/CBMI.2012.6269806"},{"key":"15779_CR12","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15779_CR13","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 4171\u20134186"},{"issue":"11","key":"15779_CR14","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1109\/TVCG.2010.266","volume":"17","author":"M Eitz","year":"2010","unstructured":"Eitz M, Hildebrand K, Boubekeur T, Alexa M (2010) Sketch-based image retrieval: Benchmark and bag-of-features descriptors. IEEE Trans Vis Comput Graph (TVCG) 17(11):1624\u20131636","journal-title":"IEEE Trans Vis Comput Graph (TVCG)"},{"issue":"2","key":"15779_CR15","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis (IJCV) 88(2):303\u2013338","journal-title":"Int J Comput Vis (IJCV)"},{"key":"15779_CR16","doi-asserted-by":"crossref","unstructured":"Fellbaum C (2012) Wordnet. The encyclopedia of applied linguistics","DOI":"10.1002\/9781405198431.wbeal1285"},{"key":"15779_CR17","unstructured":"Ge S, Goswami V, Zitnick CL, Parikh D (2020) Creative sketch generation. arXiv preprint arXiv:2011.10039"},{"key":"15779_CR18","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"15779_CR19","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"15779_CR20","doi-asserted-by":"crossref","unstructured":"Glodek M, Tschechne S, Layher G, Schels M, Brosch T, Scherer S, K\u00e4chele M, Schmidt M, Neumann H, Palm G et al (2011) Multiple classifier systems for the classification of audio-visual emotional states. In: Proceedings of the International Conference on Affective Computing and Intelligent Interaction (ACII), pp 359\u2013368 Springer","DOI":"10.1007\/978-3-642-24571-8_47"},{"key":"15779_CR21","unstructured":"Ha D, Eck D (2017) A neural representation of sketch drawings. Proceedings of the International Conference on Learning Representations (ICLR)"},{"issue":"9","key":"15779_CR22","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 37(9):1904\u20131916","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"15779_CR23","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"15779_CR24","unstructured":"Hofmann T (2013) Probabilistic latent semantic analysis. Proceedings of the conference on Uncertainty in Artificial Intelligence (UAI)"},{"key":"15779_CR25","unstructured":"Hsieh T-I, Lo Y-C, Chen H-T, Liu T-L (2019) One-shot object detection with co-attention and co-excitation. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS), pp 2721\u20132730"},{"issue":"7","key":"15779_CR26","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.cviu.2013.02.005","volume":"117","author":"R Hu","year":"2013","unstructured":"Hu R, Collomosse J (2013) A performance evaluation of gradient field hog descriptor for sketch based image retrieval. Comp Vision Image Underst (CVIU) 117(7):790\u2013806","journal-title":"Comp Vision Image Underst (CVIU)"},{"key":"15779_CR27","doi-asserted-by":"crossref","unstructured":"Hu H, Gu J, Zhang Z, Dai J, Wei Y (2018) Relation networks for object detection. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 3588\u20133597","DOI":"10.1109\/CVPR.2018.00378"},{"key":"15779_CR28","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 2011\u20132023","DOI":"10.1109\/CVPR.2018.00745"},{"key":"15779_CR29","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.inffus.2013.12.002","volume":"19","author":"AP James","year":"2014","unstructured":"James AP, Dasarathy BV (2014) Medical image fusion: A survey of the state of the art. Information Fusion 19:4\u201319","journal-title":"Information Fusion"},{"key":"15779_CR30","unstructured":"Jongejan J, Rowley H, Kawashima T, Kim J, Fox-Gieg N (2016) The quick, draw!-ai experiment. https:\/\/quickdraw.withgoogle.com"},{"key":"15779_CR31","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Liu H, Jiang Y, Shi J (2019) Foveabox: Beyond anchor-based object detector. IEEE Trans Image Process (TIP), 7389\u20137398","DOI":"10.1109\/TIP.2020.3002345"},{"issue":"1","key":"15779_CR32","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L-J, Shamma DA et al (2017) Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis (IJCV) 123(1):32\u201373","journal-title":"Int J Comput Vis (IJCV)"},{"issue":"1","key":"15779_CR33","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/s11042-013-1391-2","volume":"71","author":"Z-z Lan","year":"2014","unstructured":"Lan Z-z, Bao L, Yu S-I, Liu W, Hauptmann AG (2014) Multimedia classification and event detection using double fusion. Multimedia Tools and Applications 71(1):333\u2013347","journal-title":"Multimedia Tools and Applications"},{"issue":"10","key":"15779_CR34","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TMM.2018.2811621","volume":"20","author":"X Li","year":"2018","unstructured":"Li X, Jiang S (2018) Bundled object context for referring expressions. IEEE Transactions on Multimedia (TOMM) 20(10):2749\u20132760","journal-title":"IEEE Transactions on Multimedia (TOMM)"},{"issue":"5","key":"15779_CR35","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"J Li","year":"2017","unstructured":"Li J, Wei Y, Liang X, Dong J, Xu T, Feng J, Yan S (2017) Attentive contexts for object detection. IEEE Transactions on Multimedia (TOMM) 19(5):944\u2013954","journal-title":"IEEE Transactions on Multimedia (TOMM)"},{"key":"15779_CR36","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"15779_CR37","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 2999\u20133007","DOI":"10.1109\/ICCV.2017.324"},{"key":"15779_CR38","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft COCO: Common objects in context. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15779_CR39","doi-asserted-by":"crossref","unstructured":"Li K, Pang K, Song J, Song Y-Z, Xiang T, Hospedales TM, Zhang H (2018) Universal sketch perceptual grouping. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 582\u2013597","DOI":"10.1007\/978-3-030-01237-3_36"},{"key":"15779_CR40","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"15779_CR41","doi-asserted-by":"crossref","unstructured":"Liu L, Shen F, Shen Y, Liu X, Shao L (2017) Deep sketch hashing: Fast free-hand sketch-based image retrieval. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 2298\u20132307","DOI":"10.1109\/CVPR.2017.247"},{"key":"15779_CR42","doi-asserted-by":"crossref","unstructured":"Liu Y, Wan B, Zhu X, He X (2020) Learning cross-modal context graph for visual grounding. In: Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI), pp 11645\u201311652","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"15779_CR43","doi-asserted-by":"crossref","unstructured":"Luo R, Zhang N, Han B, Yang L (2020) Context-aware zero-shot recognition. In: Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI), pp 11709\u201311716","DOI":"10.1609\/aaai.v34i07.6841"},{"key":"15779_CR44","doi-asserted-by":"crossref","unstructured":"Morency L-P, Mihalcea R, Doshi P (2011) Towards multimodal sentiment analysis: Harvesting opinions from the web. In: Proceedings of the International Conference on Multimodal Interfaces (ICMI), pp 169\u2013176","DOI":"10.1145\/2070481.2070509"},{"key":"15779_CR45","doi-asserted-by":"crossref","unstructured":"Nagarajan T, Grauman K (2018) Attributes as operators: factorizing unseen attribute-object compositions. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 169\u2013185","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"15779_CR46","first-page":"14200","volume":"34","author":"A Nagrani","year":"2021","unstructured":"Nagrani A, Yang S, Arnab A, Jansen A, Schmid C, Sun C (2021) Attention bottlenecks for multimodal fusion. Proceedings of the Conference on Neural Information Processing Systems (NIPS) 34:14200\u201314213","journal-title":"Proceedings of the Conference on Neural Information Processing Systems (NIPS)"},{"key":"15779_CR47","unstructured":"Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. In: Getoor L, Scheffer T (eds.) Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011. Omnipress, ??? pp 689\u2013696 https:\/\/icml.cc\/2011\/papers\/399_icmlpaper.pdf"},{"key":"15779_CR48","doi-asserted-by":"crossref","unstructured":"Noh H, Hongsuck\u00a0Seo P, Han B (2016) Image question answering using convolutional neural network with dynamic parameter prediction. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit, pp 30\u201338","DOI":"10.1109\/CVPR.2016.11"},{"key":"15779_CR49","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.cviu.2019.05.001","volume":"185","author":"A Osman","year":"2019","unstructured":"Osman A, Samek W (2019) Drau: Dual recurrent attention units for visual question answering. Comp Vision Image Underst (CVIU) 185:24\u201330","journal-title":"Comp Vision Image Underst (CVIU)"},{"key":"15779_CR50","unstructured":"P\u00e9rez-Rosas V, Mihalcea R, Morency L (2013) Utterance-level multimodal sentiment analysis. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, 4-9 August 2013, Sofia, Bulgaria, Volume 1: Long Papers. The Association for Computer Linguistics, ??? pp 973\u2013982 https:\/\/aclanthology.org\/P13-1096\/"},{"key":"15779_CR51","doi-asserted-by":"crossref","unstructured":"Pham T-T, Maillot NE, Lim J-H, Chevallet J-P (2007) Latent semantic fusion model for image retrieval and annotation. In: Proceedings of the ACM Conference on Conference on Information and Knowledge Management (CIKM), pp 439\u2013444","DOI":"10.1145\/1321440.1321503"},{"key":"15779_CR52","doi-asserted-by":"crossref","unstructured":"Plummer BA, Kordas P, Hadi\u00a0Kiapour M, Zheng S, Piramuthu R, Lazebnik S (2018) Conditional image-text embedding networks. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 249\u2013264","DOI":"10.1007\/978-3-030-01258-8_16"},{"issue":"9","key":"15779_CR53","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G Potamianos","year":"2003","unstructured":"Potamianos G, Neti C, Gravier G, Garg A, Senior AW (2003) Recent advances in the automatic recognition of audiovisual speech. Proc IEEE 91(9):1306\u20131326","journal-title":"Proc IEEE"},{"key":"15779_CR54","doi-asserted-by":"crossref","unstructured":"Qi Y, Song Y-Z, Xiang T, Zhang H, Hospedales T, Li Y, Guo J (2015) Making better use of edges via perceptual grouping. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 1856\u20131865","DOI":"10.1109\/CVPR.2015.7298795"},{"key":"15779_CR55","unstructured":"Rahman S, Khan S, Barnes N (2018) Polarity loss for zero-shot object detection. arXiv preprint arXiv:1811.08982"},{"key":"15779_CR56","doi-asserted-by":"crossref","unstructured":"Rahman S, Khan S, Porikli F (2018) Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp 547\u2013563 Springer","DOI":"10.1007\/978-3-030-20887-5_34"},{"key":"15779_CR57","doi-asserted-by":"crossref","unstructured":"Rajagopalan SS, Morency L-P, Baltrusaitis T, Goecke R (2016) Extending long short-term memory for multi-view structured learning. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 338\u2013353 Springer","DOI":"10.1007\/978-3-319-46478-7_21"},{"key":"15779_CR58","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"15779_CR59","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"issue":"6","key":"15779_CR60","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 39(6):1137\u20131149","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"15779_CR61","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: Towards real-time object detection with region proposal networks. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS), pp 91\u201399"},{"key":"15779_CR62","doi-asserted-by":"crossref","unstructured":"Ren J, Hu Y, Tai Y-W, Wang C, Xu L, Sun W, Yan Q (2016) Look, listen and learn-a multimodal lstm for speaker identification. In: Proceedings of the Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI), vol 30","DOI":"10.1609\/aaai.v30i1.10471"},{"issue":"3","key":"15779_CR63","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MIS.2013.9","volume":"28","author":"VP Rosas","year":"2013","unstructured":"Rosas VP, Mihalcea R, Morency L-P (2013) Multimodal sentiment analysis of spanish online videos. IEEE Intell Syst 28(3):38\u201345","journal-title":"IEEE Intell Syst"},{"issue":"4","key":"15779_CR64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925954","volume":"35","author":"P Sangkloy","year":"2016","unstructured":"Sangkloy P, Burnell N, Ham C, Hays J (2016) The sketchy database: learning to retrieve badly drawn bunnies. ACM Trans Graph (TOG) 35(4):1\u201312","journal-title":"ACM Trans Graph (TOG)"},{"key":"15779_CR65","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Lecun Y (2013) Overfeat: Integrated recognition, localization and detection using convolutional networks. Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"15779_CR66","doi-asserted-by":"crossref","unstructured":"Shen Y, Liu L, Shen F, Shao L (2018) Zero-shot sketch-image hashing. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 3598\u20133607","DOI":"10.1109\/CVPR.2018.00379"},{"key":"15779_CR67","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video Google: A text retrieval approach to object matching in videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"issue":"2","key":"15779_CR68","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1109\/T-AFFC.2011.37","volume":"3","author":"M Soleymani","year":"2011","unstructured":"Soleymani M, Pantic M, Pun T (2011) Multimodal emotion recognition in response to videos. IEEE Trans Affect Comput (TAC) 3(2):211\u2013223","journal-title":"IEEE Trans Affect Comput (TAC)"},{"key":"15779_CR69","first-page":"632","volume":"2020","author":"Y-Z Song","year":"2020","unstructured":"Song Y-Z (2020) B\u00e9ziersketch: A generative model for scalable vector sketches. Proceedings of the proceedings of the European Conference on Computer Vision (ECCV) 2020:632\u2013647","journal-title":"Proceedings of the proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"15779_CR70","doi-asserted-by":"crossref","unstructured":"Song J, Yu Q, Song Y-Z, Xiang T, Hospedales T.M (2017) Deep spatial-semantic attention for fine-grained sketch-based image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 5552\u20135561","DOI":"10.1109\/ICCV.2017.592"},{"key":"15779_CR71","doi-asserted-by":"crossref","unstructured":"Tripathi A, Dani RR, Mishra A, Chakraborty A (2020) Sketch-guided object localization in natural images. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 532\u2013547 Springer","DOI":"10.1007\/978-3-030-58539-6_32"},{"issue":"2","key":"15779_CR72","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. International Journal of Computer Vision (IJCV) 104(2):154\u2013171","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"15779_CR73","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.inffus.2021.07.009","volume":"77","author":"S Uppal","year":"2022","unstructured":"Uppal S, Bhagat S, Hazarika D, Majumder N, Poria S, Zimmermann R, Zadeh A (2022) Multimodal research in vision and language: A review of current and emerging trends. Information Fusion 77:149\u2013171","journal-title":"Information Fusion"},{"key":"15779_CR74","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: A neural image caption generator. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"15779_CR75","doi-asserted-by":"crossref","unstructured":"Vo N, Jiang L, Sun C, Murphy K, Li L, Fei-Fei L, Hays J (2019) Composing text and image for image retrieval - an empirical odyssey. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 6439\u20136448","DOI":"10.1109\/CVPR.2019.00660"},{"issue":"7","key":"15779_CR76","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1109\/TMM.2015.2431492","volume":"17","author":"S Wang","year":"2015","unstructured":"Wang S, Zhang J, Han TX, Miao Z (2015) Sketch-based image retrieval through hypothesis-driven object boundary selection with hlr descriptor. IEEE Transactions on Multimedia (TOMM) 17(7):1045\u20131057","journal-title":"IEEE Transactions on Multimedia (TOMM)"},{"issue":"2","key":"15779_CR77","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang L, Li Y, Huang J, Lazebnik S (2018) Learning two-branch neural networks for image-text matching tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 41(2):394\u2013407","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"15779_CR78","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"15779_CR79","doi-asserted-by":"crossref","unstructured":"Wang C, Ren W, Huang K, Tan T (2014) Weakly supervised object localization with latent category learning. In: Fleet DJ, Pajdla T, Schiele B, Tuytelaars T (eds.) Proceedings of the Proceedings of the European Conference on Computer Vision, vol. 8694. Springer, ??? pp 431\u2013445","DOI":"10.1007\/978-3-319-10599-4_28"},{"key":"15779_CR80","doi-asserted-by":"crossref","unstructured":"Xu P, Huang Y, Yuan T, Pang K, Song Y-Z, Xiang T, Hospedales TM, Ma Z, Guo J (2018) Sketchmate: Deep hashing for million-scale human sketch retrieval. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 8090\u20138098","DOI":"10.1109\/CVPR.2018.00844"},{"key":"15779_CR81","unstructured":"Xu P, Joshi CK, Bresson X (2021) Multigraph transformer for free-hand sketch recognition. IEEE Transactions on Neural Networks and Learning Systems, 1\u201312"},{"key":"15779_CR82","doi-asserted-by":"crossref","unstructured":"Yan X, Chen Z, Xu A, Wang X, Liang X, Lin L (2019) Meta R-CNN: Towards general solver for instance-level low-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 9576\u20139585","DOI":"10.1109\/ICCV.2019.00967"},{"key":"15779_CR83","doi-asserted-by":"crossref","unstructured":"Yang J, Lu J, Lee S, Batra D, Parikh D (2018) Graph r-cnn for scene graph generation. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 670\u2013685","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"15779_CR84","doi-asserted-by":"crossref","unstructured":"Yi J, Wu P, Metaxas DN (2019) ASSD: attentive single shot multibox detector. Comp Vision Image Underst (CVIU) 189","DOI":"10.1016\/j.cviu.2019.102827"},{"issue":"3","key":"15779_CR85","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11263-016-0932-3","volume":"122","author":"Q Yu","year":"2017","unstructured":"Yu Q, Yang Y, Liu F, Song Y-Z, Xiang T, Hospedales TM (2017) Sketch-a-net: A deep neural network that beats humans. Int J Comput Vis (IJCV) 122(3):411\u2013425","journal-title":"Int J Comput Vis (IJCV)"},{"key":"15779_CR86","doi-asserted-by":"crossref","unstructured":"Yu Q, Liu F, Song Y-Z, Xiang T, Hospedales TM, Loy C-C (2016) Sketch me that shoe. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp 799\u2013807","DOI":"10.1109\/CVPR.2016.93"},{"key":"15779_CR87","doi-asserted-by":"crossref","unstructured":"Zadeh A, Chen M, Poria S, Cambria E, Morency L-P (2017) Tensor fusion network for multimodal sentiment analysis. Proceedings of the conference on Empirical Methods in Natural Language Processing (EMNLP), 1103\u20131114","DOI":"10.18653\/v1\/D17-1115"},{"key":"15779_CR88","doi-asserted-by":"crossref","unstructured":"Zadeh A, Liang PP, Mazumder N, Poria S, Cambria E, Morency L-P (2018) Memory fusion network for multi-view sequential learning. In: Proceedings of the Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI), vol 32","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"15779_CR89","unstructured":"Zadeh A, Zellers R, Pincus E, Morency L-P (2016) Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv preprint arXiv:1606.06259"},{"issue":"8","key":"15779_CR90","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1109\/TMM.2016.2568138","volume":"18","author":"Y Zhang","year":"2016","unstructured":"Zhang Y, Qian X, Tan X, Han J, Tang Y (2016) Sketch-based image retrieval by salient contour reinforcement. IEEE Transactions on Multimedia (TOMM) 18(8):1604\u20131615","journal-title":"IEEE Transactions on Multimedia (TOMM)"},{"key":"15779_CR91","doi-asserted-by":"crossref","unstructured":"Zhang J, Shen F, Liu L, Zhu F, Yu M, Shao L, Tao\u00a0Shen H, Van\u00a0Gool L (2018) Generative domain-migration hashing for sketch-to-image retrieval. In: Proceedings of the Proceedings of the European Conference on Computer Vision (ECCV), pp 304\u2013321","DOI":"10.1007\/978-3-030-01216-8_19"},{"key":"15779_CR92","doi-asserted-by":"crossref","unstructured":"Zimmermann RS, Siems JN (2019) Faster training of mask R-CNN by focusing on instance boundaries. Computer Vision Image Understanding (CVIU) 188","DOI":"10.1016\/j.cviu.2019.102795"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15779-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15779-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15779-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T10:41:02Z","timestamp":1706265662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15779-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,11]]},"references-count":92,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["15779"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15779-y","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,7,11]]},"assertion":[{"value":"3 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}