{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T15:50:03Z","timestamp":1749225003102,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695439"},{"type":"electronic","value":"9783030695446"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-69544-6_27","type":"book-chapter","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:05:00Z","timestamp":1614251100000},"page":"444-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["In Defense of LSTMs for Addressing Multiple Instance Learning Problems"],"prefix":"10.1007","author":[{"given":"Kaili","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Oramas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinne","family":"Tuytelaars","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,26]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Sammut, C., Webb, G.I.: Multi-instance learning. Encyclopedia of Machine Learning (2011)","DOI":"10.1007\/978-0-387-30164-8"},{"key":"27_CR2","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Schl\u00fcter, R., Ney, H.: LSTM neural networks for language modeling (2012)","DOI":"10.21437\/Interspeech.2012-65"},{"key":"27_CR4","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 3104\u20133112. Curran Associates, Inc. (2014)"},{"key":"27_CR5","unstructured":"Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: ICML. JMLR Workshop and Conference Proceedings, JMLR.org (2014)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3d human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV (2016)","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"27_CR7","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., WOO, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28, pp. 802\u2013210. Curran Associates, Inc. (2015)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Zhu, W., Lan, C., Xing, J., Zeng, W., Li, Y., Shen, L., Xie, X.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10451"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.216"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Networks, pp. 5\u20136 (2005)","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"27_CR12","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"1999","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12, 2451\u20132471 (1999)","journal-title":"Neural Comput."},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.artint.2013.06.003","volume":"201","author":"J Amores","year":"2013","unstructured":"Amores, J.: Multiple instance classification: review, taxonomy and comparative study. Artif. Intell. 201, 81\u2013105 (2013)","journal-title":"Artif. Intell."},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Carbonneau, M.A., Cheplygina, V., Granger, E., Gagnon, G.: Multiple instance learning: a survey of problem characteristics and applications. ArXiv abs\/1612.03365 (2018)","DOI":"10.1016\/j.patcog.2017.10.009"},{"key":"27_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S026988890999035X","volume":"25","author":"J Foulds","year":"2010","unstructured":"Foulds, J., Frank, E.: A review of multi-instance learning assumptions. Knowledge Eng. Rev. 25, 1\u201325 (2010)","journal-title":"Knowledge Eng. Rev."},{"key":"27_CR16","unstructured":"LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Yoo, D., Kim, N., Park, S., Paek, A.S., Kweon, I.: Pixel-level domain transfer. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_31"},{"key":"27_CR18","unstructured":"Ilse, M., Tomczak, J.M., Welling, M.: Attention-based deep multiple instance learning. arXiv preprint arXiv:1802.04712 (2018)"},{"key":"27_CR19","unstructured":"Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. CoRR abs\/1410.5401 (2014)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. Nature (2016)","DOI":"10.1038\/nature20101"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Jiang, Y.G., Davis, L.S.: Learning fashion compatibility with bidirectional LSTMS. In: ACM MM. MM 2017 (2017)","DOI":"10.1145\/3123266.3123394"},{"key":"27_CR22","unstructured":"Yazici, V.O., Gonzalez-Garcia, A., Ramisa, A., Twardowski, B., van de Weijer, J.: Orderless recurrent models for multi-label classification (2019)"},{"key":"27_CR23","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R.R., Smola, A.J.: Deep sets. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30, pp. 3391\u20133401. Curran Associates, Inc. (2017)"},{"key":"27_CR24","unstructured":"Pabbaraju, C., Jain, P.: Learning functions over sets via permutation adversarial networks. CoRR abs\/1907.05638 (2019)"},{"key":"27_CR25","unstructured":"Ramon, J., De Raedt, L.: Multiple instance neural networks. In: ICML Workshop on Attribute-value and Relational Learning (2000)"},{"key":"27_CR26","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patcog.2017.08.026","volume":"74","author":"X Wang","year":"2018","unstructured":"Wang, X., Yan, Y., Tang, P., Bai, X., Liu, W.: Revisiting multiple instance neural networks. Pattern Recognition 74, 15\u201324 (2018)","journal-title":"Pattern Recognition"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yan, J., Ouyang, W.: Quality aware network for set to set recognition (2017)","DOI":"10.1109\/CVPR.2017.499"},{"key":"27_CR28","unstructured":"Yan, Y., Wang, X., Guo, X., Fang, J., Liu, W., Huang, J.: Deep multi-instance learning with dynamic pooling. In: Asian Conference on Machine Learning (2018)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Tibo, A., Jaeger, M., Frasconi, P.: Learning and interpreting multi-multi-instance learning networks. arXiv:1810.11514 (2018)","DOI":"10.1007\/978-3-319-71249-9_44"},{"key":"27_CR30","unstructured":"Tu, M., Huang, J., He, X., Zhou, B.: Multiple instance learning with graph neural networks. In: ICML Workshop on Learning and Reasoning with Graph-Structured Representations (2019)"},{"key":"27_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR33","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 26, pp. 3111\u20133119. Curran Associates, Inc. (2013)"},{"key":"27_CR34","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: arXiv:1810.04805 (2018)"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Fernando, B., Gavves, E., Oramas M., J., Ghodrati, A., Tuytelaars, T.: Rank pooling for action recognition. In: TPAMI (2016)","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"27_CR36","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TPAMI.2017.2769085","volume":"40","author":"H Bilen","year":"2018","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A.: Action recognition with dynamic image networks. TPAMI 40, 2799\u20132813 (2018)","journal-title":"TPAMI"},{"key":"27_CR37","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: International Conference on Learning Representations (2019)"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Yang, X., Deng, C., Zheng, F., Yan, J., Liu, W.: Deep spectral clustering using dual autoencoder network. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00419"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Suzgun, M., Gehrmann, S., Belinkov, Y., Shieber, S.M.: LSTM networks can perform dynamic counting. ACL 2019 Workshop on Deep Learning and Formal Languages (2019)","DOI":"10.18653\/v1\/W19-3905"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Multiple queries for large scale specific object retrieval. In: BMVC (2012)","DOI":"10.5244\/C.26.92"},{"key":"27_CR42","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/nature05384","volume":"445","author":"L Ricci-Vitiani","year":"2007","unstructured":"Ricci-Vitiani, L., Lombardi, D.G., Pilozzi, E., Biffoni, M., Todaro, M., Peschle, C., De Maria, R.: Identification and expansion of human colon-cancer-initiating cells. Nature 445, 111\u2013115 (2007)","journal-title":"Nature"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Sirinukunwattana, K., Raza, S.E.A., Tsang, Y., Snead, D.R.J., Cree, I.A., Rajpoot, N.M.: Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. In: IEEE Transactions on Medical Imaging (2016)","DOI":"10.1109\/TMI.2016.2525803"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion gan for future-flow embedded video prediction. In: International Conference on Computer Vision. Volume abs\/1708.00284. pp. 1762\u20131770 (2017)","DOI":"10.1109\/ICCV.2017.194"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69544-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T23:53:06Z","timestamp":1671407586000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69544-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695439","9783030695446"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69544-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 February 2021","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":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","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":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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 (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - 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 (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}