{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:52:48Z","timestamp":1716227568526},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"25-26","license":[{"start":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T00:00:00Z","timestamp":1583280000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T00:00:00Z","timestamp":1583280000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702136"],"award-info":[{"award-number":["61702136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Guide to Local Science and Technology Development","award":["ZY18A01"],"award-info":[{"award-number":["ZY18A01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s11042-019-08265-x","type":"journal-article","created":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T13:02:26Z","timestamp":1583326946000},"page":"18481-18494","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["What is damaged: a benchmark dataset for abnormal traffic object classification"],"prefix":"10.1007","volume":"79","author":[{"given":"Chen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Shifan","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Desheng","family":"Lyu","sequence":"additional","affiliation":[]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,3,4]]},"reference":[{"key":"8265_CR1","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition, CVPR 2005, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"8265_CR2","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. In: Proceedings ninth IEEE international conference on computer vision, ICCV 2003, pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"8265_CR3","doi-asserted-by":"publisher","unstructured":"Bin Y, Yang Y, Shen F, Xie N, Shen HT, Li X (2018) Describing video with attention based bidirectional lstm. IEEE Trans Cybern. https:\/\/doi.org\/10.1109\/TCYB.2018.2831447","DOI":"10.1109\/TCYB.2018.2831447"},{"issue":"3","key":"8265_CR4","first-page":"27","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang C-C, Lin C-J (2011) Libsvm: a library for support vector machines. ACM Trans Intell Sys Technol (TIST) 2(3):27","journal-title":"ACM Trans Intell Sys Technol (TIST)"},{"issue":"8","key":"8265_CR5","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TPAMI.2016.2608901","volume":"39","author":"X Chang","year":"2017","unstructured":"Chang X, Yu Y-L, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39 (8):1617\u20131632","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8265_CR6","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. arXiv:1405.3531","DOI":"10.5244\/C.28.6"},{"key":"8265_CR7","doi-asserted-by":"crossref","unstructured":"Cheng Z, Ding Y, He X, Zhu L, Song X, Kankanhalli MS (2018) A \u0302 3ncf: an adaptive aspect attention model for rating prediction. In: IJCAI, pp 3748\u20133754","DOI":"10.24963\/ijcai.2018\/521"},{"issue":"3","key":"8265_CR8","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"8265_CR9","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: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"9","key":"8265_CR10","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TMM.2017.2729019","volume":"19","author":"L Gao","year":"2017","unstructured":"Gao L, Guo Z, Zhang H, Xu X, Shen HT (2017) Video captioning with attention-based LSTM and semantic consistency. IEEE Trans Multimedia 19 (9):2045\u20132055","journal-title":"IEEE Trans Multimedia"},{"issue":"2","key":"8265_CR11","first-page":"19","volume":"37","author":"Y Guo","year":"2019","unstructured":"Guo Y, Cheng Z, Nie L, Wang Y, Ma J, Kankanhalli M (2019) Attentive long short-term preference modeling for personalized product search. ACM Trans Inform Sys (TOIS) 37(2):19","journal-title":"ACM Trans Inform Sys (TOIS)"},{"key":"8265_CR12","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"8265_CR13","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1109\/TIP.2017.2749147","volume":"27","author":"M Hu","year":"2018","unstructured":"Hu M, Yang Y, Shen F, Xie N, Shen HT (2018) Hashing with angular reconstructive embeddings. IEEE Trans Image Process 27(2):545\u2013555","journal-title":"IEEE Trans Image Process"},{"key":"8265_CR14","unstructured":"Inoue H (2018) Data augmentation by pairing samples for images classification. arXiv:1801.02929"},{"key":"8265_CR15","unstructured":"Khosla A, Jayadevaprakash N, Yao B, Fei-Fei L (2011) Novel dataset for fine-grained image categorization. In: First workshop on fine-grained visual categorization, IEEE conference on computer vision and pattern recognition, Colorado Springs, CO"},{"key":"8265_CR16","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: 2013 IEEE international conference on computer vision workshops, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"8265_CR17","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems 25: 26th annual conference on neural information processing systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, USA, pp 1106\u20131114"},{"key":"8265_CR18","doi-asserted-by":"crossref","unstructured":"Kummerer M, Wallis TS, Gatys LA, Bethge M (2017) Understanding low- and high-level contributions to fixation prediction. In: 2017 IEEE international conference on computer vision (ICCV), pp 4799\u20134808","DOI":"10.1109\/ICCV.2017.513"},{"issue":"5","key":"8265_CR19","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1109\/TIP.2017.2670782","volume":"26","author":"C Li","year":"2017","unstructured":"Li C, Huang Z, Yang Y, Cao J, Sun X, Shen HT (2017) Hierarchical latent concept discovery for video event detection. IEEE Trans Image Process 26(5):2149\u20132162. https:\/\/doi.org\/10.1109\/TIP.2017.2670782","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"8265_CR20","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1109\/TKDE.2017.2728531","volume":"29","author":"Z Li","year":"2017","unstructured":"Li Z, Nie F, Chang X, Yang Y (2017) Beyond trace ratio: weighted harmonic mean of trace ratios for multiclass discriminant analysis. IEEE Trans Knowl Data Eng 29(10):2100\u20132110","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"8265_CR21","doi-asserted-by":"crossref","unstructured":"Liao L, Hu R, Xiao J, Wang Q, Xiao J, Chen J (2015) Exploiting effects of parts in fine-grained categorization of vehicles. In: 2015 IEEE international conference on image processing (ICIP), pp 745\u2013749","DOI":"10.1109\/ICIP.2015.7350898"},{"key":"8265_CR22","unstructured":"Lin Y-L, Morariu VI, Hsu WH, Davis LS (2014) Jointly optimizing 3d model fitting and fine-grained classification. In: European conference on computer vision, pp 466\u2013480"},{"issue":"2","key":"8265_CR23","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"},{"issue":"3","key":"8265_CR24","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 42(3):145\u2013175","journal-title":"Int J Comput Vis"},{"key":"8265_CR25","doi-asserted-by":"publisher","unstructured":"Shen F, Xu Y, Liu L, Yang Y, Huang Z, Tao Shen H (2018) Unsupervised deep hashing with similarity-adaptive and discrete optimization. https:\/\/doi.org\/10.1109\/TPAMI.2018.2789887","DOI":"10.1109\/TPAMI.2018.2789887"},{"issue":"9","key":"8265_CR26","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1109\/TMM.2017.2699863","volume":"19","author":"F Shen","year":"2017","unstructured":"Shen F, Yang Y, Liu L, Liu W, Tao D, Shen HT (2017) Asymmetric binary coding for image search. IEEE Trans Multimed 19(9):2022\u20132032","journal-title":"IEEE Trans Multimed"},{"key":"8265_CR27","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"8265_CR28","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition international conference on learning representations"},{"key":"8265_CR29","doi-asserted-by":"crossref","unstructured":"Sochor J, Herout A, Havel J (2016) Boxcars: 3d boxes as cnn input for improved fine-grained vehicle recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 3006\u20133015","DOI":"10.1109\/CVPR.2016.328"},{"key":"8265_CR30","doi-asserted-by":"crossref","unstructured":"Stark M, Krause J, Pepik B, Meger D, Little JJ, Schiele B, Koller D (2012) Fine-grained categorization for 3d scene understanding. In: British machine vision conference 2012, pp 1\u201312","DOI":"10.5244\/C.26.36"},{"key":"8265_CR31","doi-asserted-by":"crossref","unstructured":"Sun X, Cao J, Li C, Zhu L, Shen HT (2017) Web-based semantic fragment discovery for on-line lingual-visual similarity. In: Proceedings of the thirty-first AAAI conference on artificial intelligence, February 4-9, 2017, San Francisco, California, USA, pp 182\u2013188","DOI":"10.1609\/aaai.v31i1.10490"},{"key":"8265_CR32","doi-asserted-by":"crossref","unstructured":"Sun X, Huang Z, Yin H, Shen HT (2017) An integrated model for effective saliency prediction. In: Proceedings of the thirty-first AAAI conference on artificial intelligence, February 4-9, 2017, San Francisco, California, USA, pp 274\u2013281","DOI":"10.1609\/aaai.v31i1.10514"},{"key":"8265_CR33","unstructured":"Sun X, Yao H, Ji R (2012) What are we looking for: towards statistical modeling of saccadic eye movements and visual saliency. In: 2012 IEEE conference on computer vision and pattern recognition, pp 1552\u20131559"},{"issue":"2","key":"8265_CR34","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.jvcir.2012.01.014","volume":"24","author":"X Sun","year":"2013","unstructured":"Sun X, Yao H, Ji R (2013) Visual attention modeling based on short-term environmental adaption. J Vis Commun Image Represent 24(2):171\u2013180","journal-title":"J Vis Commun Image Represent"},{"key":"8265_CR35","doi-asserted-by":"crossref","unstructured":"Sun X, Yao H, Ji R, Liu S (2009) Photo assessment based on computational visual attention model. In: Proceedings of the 17th ACM international conference on multimedia. ACM, pp 541\u2013544","DOI":"10.1145\/1631272.1631351"},{"issue":"11","key":"8265_CR36","doi-asserted-by":"publisher","first-page":"4649","DOI":"10.1109\/TIP.2014.2337758","volume":"23","author":"X Sun","year":"2014","unstructured":"Sun X, Yao H, Ji R, Liu X-M (2014) Toward statistical modeling of saccadic eye-movement and visual saliency. IEEE Trans Image Process 23(11):4649\u20134662","journal-title":"IEEE Trans Image Process"},{"key":"8265_CR37","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pp 1\u20139. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8265_CR38","unstructured":"Ho TK (1995) Random decision forests. In: Proceedings of 3rd international conference on document analysis and recognition, ICDAR 1995, pp 278\u2013282"},{"key":"8265_CR39","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Lenc K (2015) Matconvnet: convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on multimedia. ACM, pp 689\u2013692","DOI":"10.1145\/2733373.2807412"},{"key":"8265_CR40","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset"},{"key":"8265_CR41","doi-asserted-by":"crossref","unstructured":"Yang L, Luo P, Loy CC, Tang X (2015) A large-scale car dataset for fine-grained categorization and verification. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3973\u20133981","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"8265_CR42","doi-asserted-by":"publisher","unstructured":"Yang Y, Zhou J, Ai J, Bin Y, Hanjalic A, Shen HT (2018) Video captioning by adversarial lstm. IEEE Trans Image Process. https:\/\/doi.org\/10.1109\/TIP.2018.2855422","DOI":"10.1109\/TIP.2018.2855422"},{"key":"8265_CR43","doi-asserted-by":"crossref","unstructured":"Yu W, Sun X, Yang K, Rui Y, Yao H (2018) Hierarchical semantic image matching using cnn feature pyramid. Comput Vis Image Understand","DOI":"10.1016\/j.cviu.2018.01.001"},{"issue":"7","key":"8265_CR44","doi-asserted-by":"publisher","first-page":"3179","DOI":"10.1109\/TII.2017.2767557","volume":"14","author":"Z Zeng","year":"2018","unstructured":"Zeng Z, Li Z, Cheng D, Zhang H, Zhan K, Yang Y (2018) Two-stream multirate recurrent neural network for video-based pedestrian reidentification. IEEE Trans Industrial Inform 14(7):3179\u20133186","journal-title":"IEEE Trans Industrial Inform"},{"key":"8265_CR45","unstructured":"Zhuo T, Cheng Z, Zhang P, Wong Y, Kankanhalli M (2018) Unsupervised online video object segmentation with motion property understanding. arXiv:1810.03783"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08265-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08265-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08265-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T13:39:58Z","timestamp":1666013998000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08265-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,4]]},"references-count":45,"journal-issue":{"issue":"25-26","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["8265"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08265-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,4]]},"assertion":[{"value":"6 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}