{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:07:48Z","timestamp":1775815668531,"version":"3.50.1"},"reference-count":115,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.01056","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"10972-10983","source":"Crossref","is-referenced-by-count":22,"title":["SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text"],"prefix":"10.1109","author":[{"given":"Pinaki Nath","family":"Chowdhury","sequence":"first","affiliation":[{"name":"University of Surrey,SketchX, CVSSP,United Kingdom"}]},{"given":"Ayan Kumar","family":"Bhunia","sequence":"additional","affiliation":[{"name":"University of Surrey,SketchX, CVSSP,United Kingdom"}]},{"given":"Aneeshan","family":"Sain","sequence":"additional","affiliation":[{"name":"University of Surrey,SketchX, CVSSP,United Kingdom"}]},{"given":"Subhadeep","family":"Koley","sequence":"additional","affiliation":[{"name":"University of Surrey,SketchX, CVSSP,United Kingdom"}]},{"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[{"name":"University of Surrey,SketchX, CVSSP,United Kingdom"}]},{"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[{"name":"University of Surrey,SketchX, CVSSP,United Kingdom"}]}],"member":"263","reference":[{"key":"ref57","article-title":"Scenesketcher: Fine-grained image retrieval with scene sketches","author":"liu","year":"0","journal-title":"ECCV"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref59","article-title":"Show, tell and discriminate: Image captioning by self-retrieval with partially labeled data","author":"liu","year":"0","journal-title":"ECCV"},{"key":"ref58","author":"liu","year":"2018","journal-title":"Learn to combine modalities in multimodal deep learning"},{"key":"ref53","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Text Summarization Branches Out"},{"key":"ref52","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"0","journal-title":"ECCV"},{"key":"ref55","article-title":"Microsoft coco: common objects in context","author":"lin","year":"0","journal-title":"ECCV"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00679"},{"key":"ref51","author":"li","year":"2018","journal-title":"Sketch-r2cnn An attentive network for vector sketch recognition"},{"key":"ref50","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","author":"lee","year":"0","journal-title":"ICML"},{"key":"ref46","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"0","journal-title":"ICLRE"},{"key":"ref45","article-title":"Glow: Generative flow with invertible lxl convolutions","author":"kingma","year":"0","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00662"},{"key":"ref47","author":"kobayashi","year":"2023","journal-title":"Sketch-based Medical Image Retrieval"},{"key":"ref42","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"jia","year":"0","journal-title":"ICML"},{"key":"ref41","author":"hsu","year":"2018","journal-title":"Disentangling by partitioning A representation learning framework for multimodal sensory data"},{"key":"ref44","article-title":"Yilt: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"0","journal-title":"ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref49","article-title":"Towards unsupervised image captioning with shared multi-modal embeddings","author":"laina","year":"0","journal-title":"ICCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417840"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00562"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00107"},{"key":"ref4","author":"ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00537"},{"key":"ref100","article-title":"Autocomplete hand-drawn animations","author":"jun","year":"2015","journal-title":"ACM TOG"},{"key":"ref101","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462838"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_43"},{"key":"ref34","article-title":"Sketchycoco: Image generation from free-hand scene sketches","author":"gao","year":"0","journal-title":"CVPR"},{"key":"ref37","article-title":"Captioning images taken by people who are blind","author":"gurari","year":"0","journal-title":"ECCV"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01607"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref30","article-title":"An image is wort 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"ICLRE"},{"key":"ref33","author":"faghri","year":"2017","journal-title":"Vse++ Improved visual-semantic embeddings"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2335395"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","article-title":"Caricatureshop: Personalized and photorealistic caricature sketching","author":"han","year":"2018","journal-title":"IEEE TVCG"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00299"},{"key":"ref21","article-title":"Probabilistic embed-dings for cross-modal retrieval","author":"chun","year":"0","journal-title":"CVPR"},{"key":"ref28","article-title":"Nice: Non-linear independent components estimation","author":"dinh","year":"0","journal-title":"ICLRE"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00228"},{"key":"ref29","article-title":"Density estiamtion using real nvp","author":"dinh","year":"0","journal-title":"ICLRE"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.321"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00980"},{"key":"ref15","article-title":"Human-like controllable image captioning with verb-specific se-mantic roles","author":"chen","year":"0","journal-title":"CVPR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1155"},{"key":"ref97","author":"wang","year":"2022","journal-title":"Sketch-based editing and deformation of cardiac image segmentation"},{"key":"ref96","article-title":"Diverse and accurate image description using a vari-ational auto-encoder with an additive gaussian encoding space","author":"wang","year":"0","journal-title":"NeurIPS"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref11","article-title":"Adaptive fine-grained sketch-based image retrieval","author":"bhunia","year":"0","journal-title":"ECCV"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00268"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00243"},{"key":"ref16","article-title":"Infogan: interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"0","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Fs-coco: Towards understanding of freehand sketches of common objects in context","author":"chowdhury","year":"0","journal-title":"ECCV"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01448"},{"key":"ref93","article-title":"Learning factorized multimodal representations","author":"tsai","year":"0","journal-title":"ICLRE"},{"key":"ref92","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"0","journal-title":"ICML"},{"key":"ref95","article-title":"Cider: Consensus-based image description evalu-ation","author":"vedantam","year":"0","journal-title":"CVPR"},{"key":"ref94","author":"van den oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref91","article-title":"Joint multimodal learning with deep generative models","author":"suzuki","year":"0","journal-title":"ICLR Workshop"},{"key":"ref90","author":"susskind","year":"2010","journal-title":"The toronto face dataset"},{"key":"ref89","author":"stefanini","year":"2021","journal-title":"From show to tell A survey on deep learning-based image captioning"},{"key":"ref86","article-title":"Fine-grained image retrieval: the text\/sketch input dilemma","author":"song","year":"0","journal-title":"BMVC"},{"key":"ref85","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"ICLRE"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00840"},{"key":"ref81","article-title":"Cross-modal hierarchical modelling for fine-grained sketch based image retrieval","author":"sain","year":"0","journal-title":"BMVC"},{"key":"ref84","article-title":"Engaging image captioning via per-sonality","author":"shuster","year":"0","journal-title":"CVPR"},{"key":"ref83","article-title":"Attention is all you need","author":"shazeer","year":"0","journal-title":"NeurIPS"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00731"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00664"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0932-3"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"ref109","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"0","journal-title":"ICML"},{"key":"ref106","article-title":"A zero-shot framework for sketch based image retrieval","author":"yelamarthi","year":"0","journal-title":"ECCV"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref75","article-title":"Learning to disentangle factors of variation with manifold interaction","author":"reed","year":"0","journal-title":"ICML"},{"key":"ref104","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-language pre-training","author":"xue","year":"0","journal-title":"NeurIPS"},{"key":"ref74","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref105","article-title":"Deep plastic surgery: Robust and controllable image editing with human-drawn sketches","author":"yang","year":"0","journal-title":"ECCV"},{"key":"ref77","author":"rubenstein","year":"2018","journal-title":"On the latent space of wasserstein auto-encoders"},{"key":"ref102","article-title":"Deep learning for free-hand sketch: A survey","author":"xu","year":"2022","journal-title":"IEEE TPAMI"},{"key":"ref76","article-title":"Scene designer: a unified model for scene search and synthesis from sketch","author":"sampaio","year":"0","journal-title":"ICCV Workshop"},{"key":"ref103","author":"xu","year":"2022","journal-title":"Multi-modal learning with transformers A survey"},{"key":"ref2","article-title":"Spice: semantic propositional image caption evaluation","author":"anderson","year":"0","journal-title":"ECCV"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref71","article-title":"Connecting vision and language with localized narratives","author":"pont-tuset","year":"0","journal-title":"ECCV"},{"key":"ref111","article-title":"Learning long-and shortterm user literal-preference with mul-timodal hierarchical transformer network for personalized image caption","author":"zhang","year":"0","journal-title":"AAAI"},{"key":"ref70","author":"plummer","year":"2017","journal-title":"Conditional image-text embedding networks"},{"key":"ref112","author":"zhang","year":"2022","journal-title":"Distinctive image captioning via clip guided group optimization"},{"key":"ref73","author":"radford","year":"2021","journal-title":"Learning Transferable Visual Models From Natural Language Supervision"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160076"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref69","article-title":"Towards personalized image captioning via multi-modal memory networks","author":"park","year":"2018","journal-title":"IEEE TPAMI"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01249"},{"key":"ref115","article-title":"Sketchyscene: Richly-annotated scene sketches","author":"zou","year":"20","journal-title":"ECCV"},{"key":"ref63","article-title":"Learning with invariances in random features and kernel models","author":"mei","year":"0","journal-title":"COLT"},{"key":"ref66","article-title":"Cross-domain generative learning for fine-grained sketch-based image retrieval","author":"pang","year":"0","journal-title":"BMVC"},{"key":"ref113","article-title":"Places: A 10 million image database for scene recognition","author":"zhou","year":"2017","journal-title":"IEEE TPAMI"},{"key":"ref65","author":"mokady","year":"2021","journal-title":"Clip-cap Clip prefix for image captioning"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref60","article-title":"Vil-bert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"0","journal-title":"NeurIPS"},{"key":"ref62","article-title":"Diverse image captioning with context-object split latent spaces","author":"mahajan","year":"0","journal-title":"NeurIPS"},{"key":"ref61","article-title":"Latent normalizing flows for many-to-many cross-domain map-pings","author":"mahajan","year":"0","journal-title":"ICLRE"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2023,6,17]]},"end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10205110.pdf?arnumber=10205110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T18:03:50Z","timestamp":1694455430000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10205110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":115,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/cvpr52729.2023.01056","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}