{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:06:45Z","timestamp":1762272405239},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208899"},{"type":"electronic","value":"9783030208905"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20890-5_43","type":"book-chapter","created":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T11:18:34Z","timestamp":1559387914000},"page":"678-694","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects"],"prefix":"10.1007","author":[{"given":"Christian","family":"Wilms","sequence":"first","affiliation":[]},{"given":"Simone","family":"Frintrop","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,2]]},"reference":[{"issue":"11","key":"43_CR1","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TPAMI.2012.28","volume":"34","author":"B Alexe","year":"2012","unstructured":"Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. TPAMI 34(11), 2189\u20132202 (2012)","journal-title":"TPAMI"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Hermans, A., Papandreou, G., Schroff, F., Wang, P., Adam, H.: MaskLab: instance segmentation by refining object detection with semantic and direction features. In: CVPR, pp. 4013\u20134022. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00422"},{"issue":"4","key":"43_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI 40(4), 834\u2013848 (2017)","journal-title":"TPAMI"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: Scale-aware semantic image segmentation. In: CVPR, pp. 3640\u20133649. IEEE (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR, pp. 6298\u20136306. IEEE (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, M.M., Zhang, Z., Lin, W.Y., Torr, P.H.S.: BING: binarized normed gradients for objectness estimation at 300fps. In: CVPR, pp. 3286\u20133293. IEEE (2014)","DOI":"10.1109\/CVPR.2014.414"},{"key":"43_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/978-3-319-46466-4_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Dai","year":"2016","unstructured":"Dai, J., He, K., Li, Y., Ren, S., Sun, J.: Instance-sensitive fully convolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 534\u2013549. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_32"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Frintrop, S., Werner, T., Mart\u00edn Garc\u00eda, G.: Traditional saliency reloaded: a good old model in new shape. In: CVPR, pp. 82\u201390. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298603"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448. IEEE (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587. IEEE (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: NIPS, pp. 545\u2013552. MIT Press (2007)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"43_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR15","unstructured":"Hong, S., Roh, B., Kim, K.H., Cheon, Y., Park, M.: PVANet: lightweight deep neural networks for real-time object detection. arXiv preprint arXiv:1611.08588 (2016)"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Horbert, E., Mart\u00edn Garc\u00eda, G., Frintrop, S., Leibe, B.: Sequence-level object candidates based on saliency for generic object recognition on mobile systems. In: ICRA, pp. 127\u2013134. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7138990"},{"issue":"4","key":"43_CR17","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1109\/TPAMI.2015.2465908","volume":"38","author":"J Hosang","year":"2015","unstructured":"Hosang, J., Benenson, R., Doll\u00e1r, P., Schiele, B.: What makes for effective detection proposals? TPAMI 38(4), 814\u2013830 (2015)","journal-title":"TPAMI"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.: Deeply supervised salient object detection with short connections. In: CVPR, pp. 5300\u20135309. IEEE (2017)","DOI":"10.1109\/CVPR.2017.563"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Hu, H., Lan, S., Jiang, Y., Cao, Z., Sha, F.: FastMask: segment multi-scale object candidates in one shot. In: CVPR, pp. 2280\u20132288. IEEE (2017)","DOI":"10.1109\/CVPR.2017.245"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., Zhao, Q.: SALICON: reducing the semantic gap in saliency prediction by adapting deep neural networks. In: ICCV, pp. 262\u2013270. IEEE (2015)","DOI":"10.1109\/ICCV.2015.38"},{"issue":"11","key":"43_CR21","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. TPAMI 20(11), 1254\u20131259 (1998)","journal-title":"TPAMI"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Klein, D.A., Frintrop, S.: Center-surround divergence of feature statistics for salient object detection. In: ICCV, pp. 2214\u20132219. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126499"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., Chen, Y.: RON: reverse connection with objectness prior networks for object detection. In: CVPR, pp. 5244\u20135252. IEEE (2017)","DOI":"10.1109\/CVPR.2017.557"},{"key":"43_CR24","unstructured":"Li, H., Liu, Y., Ouyang, W., Wang, X.: Zoom out-and-in network with recursive training for object proposal. arXiv preprint arXiv:1702.05711 (2017)"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: CVPR, pp. 4438\u20134446. IEEE (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"43_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"43_CR28","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5677.001.0001","volume-title":"The Psychology of Attention","author":"H Pashler","year":"1997","unstructured":"Pashler, H.: The Psychology of Attention. MIT Press, Cambridge (1997)"},{"key":"43_CR29","unstructured":"Pinheiro, P.O., Collobert, R., Doll\u00e1r, P.: Learning to segment object candidates. In: NIPS, pp. 1990\u20131998. MIT Press (2015)"},{"key":"43_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-319-46448-0_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"PO Pinheiro","year":"2016","unstructured":"Pinheiro, P.O., Lin, T.-Y., Collobert, R., Doll\u00e1r, P.: Learning to refine object segments. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 75\u201391. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_5"},{"issue":"1","key":"43_CR31","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2017","unstructured":"Pont-Tuset, J., Arbelaez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. TPAMI 39(1), 128\u2013140 (2017)","journal-title":"TPAMI"},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Qiao, S., Shen, W., Qiu, W., Liu, C., Yuille, A.: ScaleNet: guiding object proposal generation in supermarkets and beyond. In: ICCV, pp. 1809\u20131818. IEEE (2017)","DOI":"10.1109\/ICCV.2017.199"},{"key":"43_CR33","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779\u2013788. IEEE (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"43_CR34","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399. MIT Press (2015)"},{"key":"43_CR35","doi-asserted-by":"crossref","unstructured":"Treisman, A.M., Gelade, G.: Cogn. Psychol. 12 (1980)","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"43_CR36","unstructured":"Tsotsos, J.K.: An inhibitory beam for attentional selection. In: Harris, L.R., Jenkin, M. (eds.) Spatial Vision in Humans and Robots. Cambridge University Press (1993)"},{"issue":"2","key":"43_CR37","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"key":"43_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-20904-3_4","volume-title":"Computer Vision Systems","author":"T Werner","year":"2015","unstructured":"Werner, T., Mart\u00edn-Garc\u00eda, G., Frintrop, S.: Saliency-guided object candidates based on gestalt principles. In: Nalpantidis, L., Kr\u00fcger, V., Eklundh, J.-O., Gasteratos, A. (eds.) ICVS 2015. LNCS, vol. 9163, pp. 34\u201344. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-20904-3_4"},{"key":"43_CR39","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1037\/0096-1523.15.3.419","volume":"15","author":"JM Wolfe","year":"1989","unstructured":"Wolfe, J.M., Cave, K., Franzel, S.: Guided search: an alternative to the feature integration model for visual search. J. Exp. Psychol. Hum. Percept. Perform. 15, 97\u2013136 (1989)","journal-title":"J. Exp. Psychol. Hum. Percept. Perform."},{"key":"43_CR40","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057. PMLR (2015)"},{"key":"43_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329. IEEE (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"43_CR42","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR, pp. 4651\u20134659. IEEE (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"43_CR43","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"43_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20890-5_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T23:49:26Z","timestamp":1694908166000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20890-5_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208899","9783030208905"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20890-5_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}