{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:37:00Z","timestamp":1784821020725,"version":"3.55.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01252-6_27","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T09:48:05Z","timestamp":1538732885000},"page":"454-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["TS$$^{2}$$C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection"],"prefix":"10.1007","author":[{"given":"Yunchao","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghui","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjun","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Bilen, H., Pedersoli, M., Tuytelaars, T.: Weakly supervised object detection with posterior regularization. In: BMVC, pp. 1\u201312 (2014)","DOI":"10.5244\/C.28.52"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bilen, H., Pedersoli, M., Tuytelaars, T.: Weakly supervised object detection with convex clustering. In: IEEE CVPR, pp. 1081\u20131089 (2015)","DOI":"10.1109\/CVPR.2015.7298711"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: IEEE CVPR, pp. 2846\u20132854 (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"27_CR4","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. preprint arXiv:1412.7062 (2014)"},{"key":"27_CR5","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: NIPS, pp. 424\u2013432 (2015)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Wei, Y., Shi, H., Feris, R., Xiong, J., Huang, T.: Revisiting RCNN: on awakening the classification power of faster RCNN. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_28"},{"issue":"1","key":"27_CR7","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TPAMI.2016.2535231","volume":"39","author":"RG Cinbis","year":"2017","unstructured":"Cinbis, R.G., Verbeek, J., Schmid, C.: Weakly supervised object localization with multi-fold multiple instance learning. IEEE TPAMI 39(1), 189\u2013203 (2017)","journal-title":"IEEE TPAMI"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"3","key":"27_CR9","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s11263-012-0538-3","volume":"100","author":"T Deselaers","year":"2012","unstructured":"Deselaers, T., Alexe, B., Ferrari, V.: Weakly supervised localization and learning with generic knowledge. IJCV 100(3), 275\u2013293 (2012)","journal-title":"IJCV"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Pazandeh, A., Pirsiavash, H., Van Gool, L.: Weakly supervised cascaded convolutional networks. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.545"},{"issue":"1","key":"27_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2014","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV 111(1), 98\u2013136 (2014)","journal-title":"IJCV"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: IEEE ICCV, pp. 1134\u20131142 (2015)","DOI":"10.1109\/ICCV.2015.135"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"27_CR15","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":"27_CR16","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACM Multimedia, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Jie, Z., Wei, Y., Jin, X., Feng, J., Liu, W.: Deep self-taught learning for weakly supervised object localization. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.457"},{"key":"27_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-319-46454-1_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Kantorov","year":"2016","unstructured":"Kantorov, V., Oquab, M., Cho, M., Laptev, I.: ContextLocNet: context-aware deep network models for weakly supervised localization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 350\u2013365. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_22"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Lampert, C.H.: Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In: ECCV, pp. 695\u2013711 (2016)","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Lai, B., Gong, X.: Saliency guided end-to-end learning for weakly supervised object detection. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/285"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Li, D., Huang, J.B., Li, Y., Wang, S., Yang, M.H.: Weakly supervised object localization with progressive domain adaptation. In: IEEE CVPR, pp. 3512\u20133520 (2016)","DOI":"10.1109\/CVPR.2016.382"},{"issue":"5","key":"27_CR22","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"J Li","year":"2017","unstructured":"Li, J., et al.: Attentive contexts for object detection. IEEE Trans. Multimedia 19(5), 944\u2013954 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Liang, X., Liu, S., Wei, Y., Liu, L., Lin, L., Yan, S.: Towards computational baby learning: a weakly-supervised approach for object detection. In: IEEE ICCV, pp. 999\u20131007 (2015)","DOI":"10.1109\/ICCV.2015.120"},{"key":"27_CR24","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. In: ICLR (2013)"},{"key":"27_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free?-weakly-supervised learning with convolutional neural networks. In: IEEE CVPR, pp. 685\u2013694 (2015)","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"27_CR29","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 (2015)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: IEEE ICCV (2017)","DOI":"10.1109\/ICCV.2017.212"},{"key":"27_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Tang, P., Wang, X., Bai, X., Liu, W.: Multiple instance detection network with online instance classifier refinement. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.326"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Teh, E.W., Rochan, M., Wang, Y.: Attention networks for weakly supervised object localization. In: BMVC (2016)","DOI":"10.5244\/C.30.52"},{"issue":"2","key":"27_CR34","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":"27_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-319-10599-4_28","volume-title":"Computer Vision \u2013 ECCV 2014","author":"C Wang","year":"2014","unstructured":"Wang, C., Ren, W., Huang, K., Tan, T.: Weakly supervised object localization with latent category learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 431\u2013445. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_28"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.687"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Wei, Y., et al.: Learning to segment with image-level annotations. Pattern Recogn. (2016)","DOI":"10.1016\/j.patcog.2016.01.015"},{"key":"27_CR38","unstructured":"Wei, Y., et al.: STC: a simple to complex framework for weakly-supervised semantic segmentation. IEEE TPAMI (2016)"},{"issue":"9","key":"27_CR39","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TPAMI.2015.2491929","volume":"38","author":"Y Wei","year":"2016","unstructured":"Wei, Y., et al.: HCP: a flexible cnn framework for multi-label image classification. IEEE TPAMI 38(9), 1901\u20131907 (2016)","journal-title":"IEEE TPAMI"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., Huang, T.S.: Revisiting dilated convolution: a simple approach for weakly-and semi-supervised semantic segmentation. In: IEEE CVPR, pp. 7268\u20137277","DOI":"10.1109\/CVPR.2018.00759"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, H., Feng, J., Wei, Y., Zhang, M., Yan, S.: Deep salient object detection with dense connections and distraction diagnosis. IEEE Trans. Multimedia (2018)","DOI":"10.1109\/TMM.2018.2830098"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Feng, J., Yang, Y., Huang, T.: Adversarial complementary learning for weakly supervised object localization. In: IEEE CVPR (2018)","DOI":"10.1109\/CVPR.2018.00144"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Kang, G., Yang, Y., Huang, T.: Self-produced guidance for weakly-supervised object localization. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, F., Li, J., Zhao, J., Feng, J.: Weakly supervised phrase localization with multi-scale anchored transformer network. In: IEEE CVPR, pp. 5696\u20135705 (2018)","DOI":"10.1109\/CVPR.2018.00597"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A.A.L., Oliva, A., Torralba, A.: Learning Deep Features for Discriminative Localization. IEEE CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Urtasun, R., Salakhutdinov, R., Fidler, S.: segDeepM: exploiting segmentation and context in deep neural networks for object detection. In: IEEE CVPR, pp. 4703\u20134711 (2015)","DOI":"10.1109\/CVPR.2015.7299102"},{"key":"27_CR47","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 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01252-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:47:56Z","timestamp":1773762476000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}