{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:57Z","timestamp":1775815197022,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,5,10]],"date-time":"2020-05-10T00:00:00Z","timestamp":1589068800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,10]],"date-time":"2020-05-10T00:00:00Z","timestamp":1589068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"2019 Tianjin New Generation Artificial Intelligence Major Program"},{"name":"2018 Tianjin New Generation Artificial Intelligence Major Program","award":["18ZXZNGX00150"],"award-info":[{"award-number":["18ZXZNGX00150"]}]},{"name":"Open Project Program of the State Key Lab of CAD & CG, Zhejiang University","award":["A2005"],"award-info":[{"award-number":["A2005"]}]},{"name":"Open Project Program of the State Key Lab of CAD & CG, Zhejiang University","award":["A2012"],"award-info":[{"award-number":["A2012"]}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61902277"],"award-info":[{"award-number":["61902277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61772359"],"award-info":[{"award-number":["61772359"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61872267"],"award-info":[{"award-number":["61872267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61702471"],"award-info":[{"award-number":["61702471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Elite Scholar Program of Tianjin University","award":["2019XRX-0035"],"award-info":[{"award-number":["2019XRX-0035"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11042-020-08973-9","type":"journal-article","created":{"date-parts":[[2020,5,10]],"date-time":"2020-05-10T00:03:31Z","timestamp":1589069011000},"page":"17169-17181","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["FRSFN: A semantic fusion network for practical fashion retrieval"],"prefix":"10.1007","volume":"80","author":[{"given":"An-An","family":"Liu","sequence":"first","affiliation":[]},{"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5864-0276","authenticated-orcid":false,"given":"Dan","family":"Song","sequence":"additional","affiliation":[]},{"given":"Wenhui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,10]]},"reference":[{"key":"8973_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka M, Pishchulin L, Gehler P (2014) Schiele, B.: 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp 3686\u20133693","DOI":"10.1109\/CVPR.2014.471"},{"issue":"12","key":"8973_CR2","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8973_CR3","doi-asserted-by":"crossref","unstructured":"Chen H, Gallagher A, Girod B (2012) Describing clothing by semantic attributes. In: European Conference on Computer Vision, Springer, pp 609\u2013623","DOI":"10.1007\/978-3-642-33712-3_44"},{"key":"8973_CR4","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2014) Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv:1412.7062"},{"key":"8973_CR5","doi-asserted-by":"crossref","unstructured":"Chen LC, Yang Y, Wang J, Xu W, Yuille AL (2016) Attention to scale: Scale-aware semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3640\u20133649","DOI":"10.1109\/CVPR.2016.396"},{"issue":"2","key":"8973_CR6","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1145\/3291060","volume":"37","author":"Z Cheng","year":"2019","unstructured":"Cheng Z, Chang X, Zhu L, Kanjirathinkal RC, Kankanhalli M (2019) Mmalfm: Explainable recommendation by leveraging reviews and images. ACM Transactions on Information Systems (TOIS) 37(2):16","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"8973_CR7","doi-asserted-by":"crossref","unstructured":"Corbiere C, Ben-Younes H, Ram\u00e9 A., Ollion C (2017) Leveraging weakly annotated data for fashion image retrieval and label prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2268\u20132274","DOI":"10.1109\/ICCVW.2017.266"},{"key":"8973_CR8","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision & Pattern Recognition"},{"key":"8973_CR9","doi-asserted-by":"crossref","unstructured":"Di W, Wah C, Bhardwaj A, Piramuthu R, Sundaresan N (2013) Style finder: Fine-grained clothing style detection and retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp 8\u201313","DOI":"10.1109\/CVPRW.2013.6"},{"key":"8973_CR10","doi-asserted-by":"crossref","unstructured":"Fang HS, Lu G, Fang X, Xie J, Tai YW, Lu C (2018) Weakly and semi supervised human body part parsing via pose-guided knowledge transfer. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, pp 70\u201378","DOI":"10.1109\/CVPR.2018.00015"},{"key":"8973_CR11","doi-asserted-by":"crossref","unstructured":"Gajic B, Baldrich R (2018) Cross-domain fashion image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1869\u20131871","DOI":"10.1109\/CVPRW.2018.00243"},{"key":"8973_CR12","doi-asserted-by":"crossref","unstructured":"Gan C, Lin M, Yang Y, De Melo G, Hauptmann AG (2016) Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition. In: Thirtieth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"8973_CR13","doi-asserted-by":"crossref","unstructured":"Gong K, Liang X, Li Y, Chen Y, Yang M, Lin L (2018) Instance-level human parsing via part grouping network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 770\u2013785","DOI":"10.1007\/978-3-030-01225-0_47"},{"key":"8973_CR14","doi-asserted-by":"crossref","unstructured":"Hadi Kiapour M, Han X, Lazebnik S, Berg AC, Berg TL (2015) Where to buy it: Matching street clothing photos in online shops. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3343\u20133351","DOI":"10.1109\/ICCV.2015.382"},{"key":"8973_CR15","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/TIP.2019.2936742","volume":"29","author":"X Han","year":"2019","unstructured":"Han X, Song X, Yao Y, Xu XS, Nie L (2019) Neural compatibility modeling with probabilistic knowledge distillation. IEEE Trans Image Process 29:871\u2013882","journal-title":"IEEE Trans Image Process"},{"key":"8973_CR16","unstructured":"Han Y, Zhu L, Cheng Z, Li J, Liu X Discrete optimal graph clustering. IEEE Transactions on Cybernetics, pp 1\u201314"},{"key":"8973_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8973_CR18","doi-asserted-by":"crossref","unstructured":"Huang J, Feris RS, Chen Q, Yan S (2015) Cross-domain image retrieval with a dual attribute-aware ranking network. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1062\u20131070","DOI":"10.1109\/ICCV.2015.127"},{"key":"8973_CR19","doi-asserted-by":"crossref","unstructured":"Kalayeh MM, Basaran E, G\u00f6kmen M, Kamasak ME, Shah M (2018) Human semantic parsing for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1062\u20131071","DOI":"10.1109\/CVPR.2018.00117"},{"issue":"4","key":"8973_CR20","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/TPAMI.2018.2820063","volume":"41","author":"X Liang","year":"2018","unstructured":"Liang X, Gong K, Shen X, Lin L (2018) Look into person: Joint body parsing & pose estimation network and a new benchmark. IEEE Trans Pattern Anal Mach Intell 41(4):871\u2013885","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"8973_CR21","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1109\/TMM.2016.2542983","volume":"18","author":"X Liang","year":"2016","unstructured":"Liang X, Lin L, Yang W, Luo P, Huang J, Yan S (2016) Clothes co-parsing via joint image segmentation and labeling with application to clothing retrieval. IEEE Trans Multimedia 18(6):1175\u20131186","journal-title":"IEEE Trans Multimedia"},{"issue":"12","key":"8973_CR22","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1109\/TPAMI.2015.2408360","volume":"37","author":"X Liang","year":"2015","unstructured":"Liang X, Liu S, Shen X, Yang J, Liu L, Dong J, Lin L, Yan S (2015) Deep human parsing with active template regression. IEEE Trans Pattern Anal Mach Intell 37(12):2402\u20132414","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8973_CR23","doi-asserted-by":"crossref","unstructured":"Liang X, Xu C, Shen X, Yang J, Liu S, Tang J, Lin L, Yan S (2015) Human parsing with contextualized convolutional neural network. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1386\u20131394","DOI":"10.1109\/ICCV.2015.163"},{"key":"8973_CR24","doi-asserted-by":"crossref","unstructured":"Lin K, Yang HF, Liu KH, Hsiao JH, Chen CS (2015) Rapid clothing retrieval via deep learning of binary codes and hierarchical search. In: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, ACM, pp 499\u2013502","DOI":"10.1145\/2671188.2749318"},{"issue":"5","key":"8973_CR25","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1109\/TIP.2016.2540802","volume":"25","author":"AA Liu","year":"2016","unstructured":"Liu AA, Nie WZ, Gao Y, Su YT (2016) Multi-modal clique-graph matching for view-based 3d model retrieval. IEEE Trans Image Process 25(5):2103\u20132116","journal-title":"IEEE Trans Image Process"},{"key":"8973_CR26","doi-asserted-by":"crossref","unstructured":"Liu S, Liang X, Liu L, Shen X, Yang J, Xu C, Lin L, Cao X, Yan S (2015) Matching-cnn meets knn: Quasi-parametric human parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1419\u20131427","DOI":"10.1109\/CVPR.2015.7298748"},{"key":"8973_CR27","doi-asserted-by":"crossref","unstructured":"Liu Z, Luo P, Qiu S, Wang X, Tang X (2016) Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1096\u20131104","DOI":"10.1109\/CVPR.2016.124"},{"issue":"2","key":"8973_CR28","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"8973_CR29","doi-asserted-by":"crossref","unstructured":"Luo Z, Yuan J, Yang J, Wen W (2019) Spatial constraint multiple granularity attention network for clothesretrieval. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp 859\u2013863","DOI":"10.1109\/ICIP.2019.8802938"},{"issue":"12","key":"8973_CR30","doi-asserted-by":"publisher","first-page":"16979","DOI":"10.1007\/s11042-018-7102-2","volume":"78","author":"W Nie","year":"2019","unstructured":"Nie W, Wang K, Wang H, Su Y (2019) The assessment of 3d model representation for retrieval with cnn-rnn networks. Multimedia Tools Appl 78 (12):16979\u201316994","journal-title":"Multimedia Tools Appl"},{"key":"8973_CR31","doi-asserted-by":"publisher","first-page":"132161","DOI":"10.1109\/ACCESS.2019.2940281","volume":"7","author":"W Nie","year":"2019","unstructured":"Nie W, Wang W, Huang X (2019) Srnet: Structured relevance feature learning network from skeleton data for human action recognition. IEEE Access 7:132161\u2013132172","journal-title":"IEEE Access"},{"key":"8973_CR32","doi-asserted-by":"crossref","unstructured":"Nie X, Feng J, Yan S (2018) Mutual learning to adapt for joint human parsing and pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 502\u2013517","DOI":"10.1007\/978-3-030-01228-1_31"},{"key":"8973_CR33","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Computer Science"},{"key":"8973_CR34","doi-asserted-by":"crossref","unstructured":"Song X, Feng F, Liu J, Li Z, Nie L, Ma J (2017) Neurostylist: Neural compatibility modeling for clothing matching. In: Proceedings of the 25th ACM International Conference on Multimedia, pp 753\u2013761","DOI":"10.1145\/3123266.3123314"},{"key":"8973_CR35","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ins.2017.10.051","volume":"429","author":"X Sun","year":"2018","unstructured":"Sun X, Liu Z, Hu Y, Zhang L, Zimmermann R (2018) Perceptual multi-channel visual feature fusion for scene categorization. Inf Sci 429:37\u201348","journal-title":"Inf Sci"},{"key":"8973_CR36","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8973_CR37","doi-asserted-by":"crossref","unstructured":"Xia F, Zhu J, Wang P, Yuille AL (2016) Pose-guided human parsing by an and\/or graph using pose-context features. In: Thirtieth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v30i1.10460"},{"issue":"1s","key":"8973_CR38","first-page":"3","volume":"15","author":"H Xie","year":"2019","unstructured":"Xie H, Fang S, Zha ZJ, Yang Y, Li Y, Zhang Y (2019) Convolutional attention networks for scene text recognition. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 15(1s):3","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"8973_CR39","doi-asserted-by":"crossref","unstructured":"Yamaguchi K, Hadi Kiapour M, Berg TL (2013) Paper doll parsing: Retrieving similar styles to parse clothing items. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3519\u20133526","DOI":"10.1109\/ICCV.2013.437"},{"key":"8973_CR40","doi-asserted-by":"crossref","unstructured":"Yamaguchi K, Kiapour MH, Ortiz LE, Berg TL (2012) Parsing clothing in fashion photographs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 3570\u20133577","DOI":"10.1109\/CVPR.2012.6248101"},{"key":"8973_CR41","doi-asserted-by":"crossref","unstructured":"Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural computing and applications, pp 1\u201320","DOI":"10.1007\/s00521-018-3579-x"},{"key":"8973_CR42","doi-asserted-by":"crossref","unstructured":"Zhang H, Li S, Cai S, Jiang H, Kuo CCJ (2018) Representative fashion feature extraction by leveraging weakly annotated online resources. In: 2018 25Th IEEE International Conference on Image Processing (ICIP), IEEE, pp 2640\u20132644","DOI":"10.1109\/ICIP.2018.8451125"},{"key":"8973_CR43","doi-asserted-by":"crossref","unstructured":"Zhao B, Feng J, Wu X, Yan S (2017) Memory-augmented attribute manipulation networks for interactive fashion search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1520\u20131528","DOI":"10.1109\/CVPR.2017.652"},{"key":"8973_CR44","doi-asserted-by":"crossref","unstructured":"Ziaeefard M, Camacaro J, Bessega C (2018) Hierarchical feature map characterization in fashion interpretation. In: 2018 15Th Conference on Computer and Robot Vision (CRV), IEEE, pp 88\u201394","DOI":"10.1109\/CRV.2018.00022"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08973-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-08973-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08973-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T10:27:41Z","timestamp":1666520861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-08973-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,10]]},"references-count":44,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["8973"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-08973-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,10]]},"assertion":[{"value":"30 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}