{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T06:50:04Z","timestamp":1784357404820,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240616","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T17:52:08Z","timestamp":1539885128000},"page":"1301-1309","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":77,"title":["WildFish"],"prefix":"10.1145","author":[{"given":"Peiqin","family":"Zhuang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"K. Anantharajah Z. Ge C. McCool S. Denman C. Fookes P. Corke D. Tjondronegoro and S. Sridharan. 2014. Local Inter-Session Variability Modelling for Object Classification. In WACV .  K. Anantharajah Z. Ge C. McCool S. Denman C. Fookes P. Corke D. Tjondronegoro and S. Sridharan. 2014. Local Inter-Session Variability Modelling for Object Classification. In WACV .","DOI":"10.1109\/WACV.2014.6836084"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"A. Bendale and T. Boult. 2015. Towards Open World Recognition. In CVPR .  A. Bendale and T. Boult. 2015. Towards Open World Recognition. In CVPR .","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"A. Bendale and T. E. Boult. 2016. Towards Open Set Deep Networks. In CVPR .  A. Bendale and T. E. Boult. 2016. Towards Open Set Deep Networks. In CVPR .","DOI":"10.1109\/CVPR.2016.173"},{"key":"e_1_3_2_1_5_1","unstructured":"B. J. Boom P. X. Huang J. He and R. B. Fisher. 2012. Supporting Ground-Truth annotation of image datasets using clustering. In ICPR .  B. J. Boom P. X. Huang J. He and R. B. Fisher. 2012. Supporting Ground-Truth annotation of image datasets using clustering. In ICPR ."},{"key":"e_1_3_2_1_6_1","volume":"201","author":"Busto P. P.","journal-title":"J. Gall."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"L. Castrejon Y. Aytar C. Vondrick H. Pirsiavash and A. Torralba. 2016. Learning Aligned Cross-Modal Representations from Weakly Aligned Data. In CVPR .  L. Castrejon Y. Aytar C. Vondrick H. Pirsiavash and A. Torralba. 2016. Learning Aligned Cross-Modal Representations from Weakly Aligned Data. In CVPR .","DOI":"10.1109\/CVPR.2016.321"},{"key":"e_1_3_2_1_8_1","unstructured":"LifeCLEF Challenges. 2017. ImageCLEF\/LifeCLEF. In http:\/\/www.imageclef.org\/.  LifeCLEF Challenges. 2017. ImageCLEF\/LifeCLEF. In http:\/\/www.imageclef.org\/."},{"key":"e_1_3_2_1_9_1","volume-title":"Xception: Deep Learning with Depthwise Separable Convolutions. In CVPR .","author":"Chollet F.","year":"2017"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2015.11"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR .  J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR .","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_12_1","unstructured":"Jeff Donahue Yangqing Jia Oriol Vinyals Judy Hoffman Ning Zhang Eric Tzeng and Trevor Darrell. 2014. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In ICML .   Jeff Donahue Yangqing Jia Oriol Vinyals Judy Hoffman Ning Zhang Eric Tzeng and Trevor Darrell. 2014. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In ICML ."},{"key":"e_1_3_2_1_13_1","unstructured":"A. Frome G. S. Corrado J. Shlens S. Bengio J. Dean M. Ranzato and T. Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In NIPS .   A. Frome G. S. Corrado J. Shlens S. Bengio J. Dean M. Ranzato and T. Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In NIPS ."},{"key":"e_1_3_2_1_14_1","volume-title":"See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition. In CVPR .","author":"Fu J.","year":"2017"},{"key":"e_1_3_2_1_15_1","unstructured":"Y. Fu T. Xiang Y. Jiang X. Xue L. Sigal and S. Gong. 2017a. Recent Advances in Zero-shot Recognition. IEEE Signal Processing Magazine (2017).  Y. Fu T. Xiang Y. Jiang X. Xue L. Sigal and S. Gong. 2017a. Recent Advances in Zero-shot Recognition. IEEE Signal Processing Magazine (2017)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Z. Ge S. Demyanov Z. Chen and R. Garnavi. 2017. Generative OpenMax for Multi-Class Open Set Classification. In BMVC .  Z. Ge S. Demyanov Z. Chen and R. Garnavi. 2017. Generative OpenMax for Multi-Class Open Set Classification. In BMVC .","DOI":"10.5244\/C.31.42"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"M. Gunther S. Cruz E. M. Rudd and T. E. Boult. 2017. Toward Open-Set Face Recognition. In CVPRW .  M. Gunther S. Cruz E. M. Rudd and T. E. Boult. 2017. Toward Open-Set Face Recognition. In CVPRW .","DOI":"10.1109\/CVPRW.2017.85"},{"key":"e_1_3_2_1_18_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. In arXiv:1512.03385 .  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. In arXiv:1512.03385 ."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"X. He and Y. Peng. 2017. Fine-Grained Image Classification via Combining Vision and Language. In CVPR .  X. He and Y. Peng. 2017. Fine-Grained Image Classification via Combining Vision and Language. In CVPR .","DOI":"10.1109\/CVPR.2017.775"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"G. Huang Z. Liu L. van der Maaten and K. Q. Weinberger. 2017. Densely Connected Convolutional Networks. In CVPR .  G. Huang Z. Liu L. van der Maaten and K. Q. Weinberger. 2017. Densely Connected Convolutional Networks. In CVPR .","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"S. Huang Z. Xu D. Tao and Y. Zhang. 2016. Part-Stacked CNN for Fine-Grained Visual Categorization. In CVPR .  S. Huang Z. Xu D. Tao and Y. Zhang. 2016. Part-Stacked CNN for Fine-Grained Visual Categorization. In CVPR .","DOI":"10.1109\/CVPR.2016.132"},{"key":"e_1_3_2_1_22_1","volume-title":"The Fifth Workshop on Fine-Grained Visual Categorization. In CVPR .","author":"Competition Naturalist","year":"2018"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"L. P. Jain W. J. Scheirer and T. E. Boult. 2014. Multi-class Open Set Recognition Using Probability of Inclusion. In ECCV .  L. P. Jain W. J. Scheirer and T. E. Boult. 2014. Multi-class Open Set Recognition Using Probability of Inclusion. In ECCV .","DOI":"10.1007\/978-3-319-10578-9_26"},{"key":"e_1_3_2_1_24_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS .   Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS ."},{"key":"e_1_3_2_1_25_1","volume":"201","author":"Lin D.","journal-title":"J. Jia."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_3_2_1_27_1","unstructured":"X. Liu T. Xia J. Wang Y. Yang F. Zhou and Y. Lin. 2017. Fully Convolutional Attention Networks for Fine-Grained Recognition. arxiv:1603.06765 (2017).  X. Liu T. Xia J. Wang Y. Yang F. Zhou and Y. Lin. 2017. Fully Convolutional Attention Networks for Fine-Grained Recognition. arxiv:1603.06765 (2017)."},{"key":"e_1_3_2_1_28_1","volume":"201","author":"Mikolov T.","journal-title":"J. Dean."},{"key":"e_1_3_2_1_29_1","volume":"201","author":"Peng Y.","journal-title":"J. Zhao."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"S. Reed Z. Akata B. Schiele and H. Lee. 2016. Learning Deep Representations of Fine-grained Visual Descriptions. In CVPR .  S. Reed Z. Akata B. Schiele and H. Lee. 2016. Learning Deep Representations of Fine-grained Visual Descriptions. In CVPR .","DOI":"10.1109\/CVPR.2016.13"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"A. Salvador N. Hynes Y. Aytar J. Marin F. Ofli I. Weber and A. Torralba. 2017. Learning Cross-Modal Embeddings for Cooking Recipes and Food Images. In CVPR .  A. Salvador N. Hynes Y. Aytar J. Marin F. Ofli I. Weber and A. Torralba. 2017. Learning Cross-Modal Embeddings for Cooking Recipes and Food Images. In CVPR .","DOI":"10.1109\/CVPR.2017.327"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"H. Sattar S. Muller M. Fritz and A. Bulling. 2015. Prediction of Search Targets From Fixations in Open-World Settings. In CVPR .  H. Sattar S. Muller M. Fritz and A. Bulling. 2015. Prediction of Search Targets From Fixations in Open-World Settings. In CVPR .","DOI":"10.1109\/CVPR.2015.7298700"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"W. J. Scheirer and T. E. Boult L. P. Jain. 2014. Probability Models for Open Set Recognition. IEEE T-PAMI (2014).  W. J. Scheirer and T. E. Boult L. P. Jain. 2014. Probability Models for Open Set Recognition. IEEE T-PAMI (2014).","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.54"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"e_1_3_2_1_36_1","volume-title":"DOC: Deep Open Classification of Text Documents. In EMNLP .","author":"Shu L.","year":"2017"},{"key":"e_1_3_2_1_37_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014).  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR .  Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR .","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Y. H. H. Tsai L. K. Huang and R. Salakhutdinov. 2017. Learning Robust Visual-Semantic Embeddings. In ICCV .  Y. H. H. Tsai L. K. Huang and R. Salakhutdinov. 2017. Learning Robust Visual-Semantic Embeddings. In ICCV .","DOI":"10.1109\/ICCV.2017.386"},{"key":"e_1_3_2_1_40_1","unstructured":"C. Wah S. Branson P. Welinder P. Perona and S. Belongie. 2011. The Caltech-UCSD Birds-200--2011 Dataset. Technical Report.  C. Wah S. Branson P. Welinder P. Perona and S. Belongie. 2011. The Caltech-UCSD Birds-200--2011 Dataset. Technical Report."},{"key":"e_1_3_2_1_41_1","unstructured":"L. Wang Y. Li J. Huang and S. Lazebnik. 2017. Learning Two-Branch Neural Networks for Image-Text Matching Tasks. IEEE TPAMI (2017).  L. Wang Y. Li J. Huang and S. Lazebnik. 2017. Learning Two-Branch Neural Networks for Image-Text Matching Tasks. IEEE TPAMI (2017)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Y. Wen K. Zhang Z. Li and Y. Qiao. 2016. A Discriminative Feature Learning Approach for Deep Face Recognition. In ECCV .  Y. Wen K. Zhang Z. Li and Y. Qiao. 2016. A Discriminative Feature Learning Approach for Deep Face Recognition. In ECCV .","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Yongqin Xian Bernt Schiele and Zeynep Akata. 2017. Zero-Shot Learning - The Good the Bad and the Ugly. In CVPR .  Yongqin Xian Bernt Schiele and Zeynep Akata. 2017. Zero-Shot Learning - The Good the Bad and the Ugly. In CVPR .","DOI":"10.1109\/CVPR.2017.328"},{"key":"e_1_3_2_1_44_1","unstructured":"T. Xiao Y. Xu K. Yang J. Zhang Y. Peng and Z. Zhang. 2015. The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In CVPR .  T. Xiao Y. Xu K. Yang J. Zhang Y. Peng and Z. Zhang. 2015. The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In CVPR ."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"S. Xie R. Girshick P. Doll\u00e1r Z. Tu and K. He. 2016. Aggregated Residual Transformations for Deep Neural Networks. In arXiv:1611.05431 .  S. Xie R. Girshick P. Doll\u00e1r Z. Tu and K. He. 2016. Aggregated Residual Transformations for Deep Neural Networks. In arXiv:1611.05431 .","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"H. Zhang T. Xu M. Elhoseiny X. Huang S. Zhang A. Elgammal and D. Metaxas. 2016b. SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition. In CVPR .  H. Zhang T. Xu M. Elhoseiny X. Huang S. Zhang A. Elgammal and D. Metaxas. 2016b. SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition. In CVPR .","DOI":"10.1109\/CVPR.2016.129"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"N. Zhang J. Donahue R. Girshick and T. Darrell. 2014. Part-based R-CNNs for Fine-grained Category Detection. In ECCV .  N. Zhang J. Donahue R. Girshick and T. Darrell. 2014. Part-based R-CNNs for Fine-grained Category Detection. In ECCV .","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"X. Zhang H. Xiong W. Zhou W. Lin and Q. Tian. 2016a. Picking Deep Filter Responses for Fine-Grained Image Recognition. In CVPR .  X. Zhang H. Xiong W. Zhou W. Lin and Q. Tian. 2016a. Picking Deep Filter Responses for Fine-Grained Image Recognition. In CVPR .","DOI":"10.1109\/CVPR.2016.128"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"H. Zhao X. Puig B. Zhou S. Fidler and A. Torralba. 2017. Open Vocabulary Scene Parsing. In CVPR .  H. Zhao X. Puig B. Zhou S. Fidler and A. Torralba. 2017. Open Vocabulary Scene Parsing. In CVPR .","DOI":"10.1109\/ICCV.2017.221"},{"key":"e_1_3_2_1_50_1","volume":"201","author":"Zheng H.","journal-title":"J. Luo."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2453984"}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 26th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240616","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:57:34Z","timestamp":1750208254000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240616"}},"subtitle":["A Large Benchmark for Fish Recognition in the Wild"],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":51,"alternative-id":["10.1145\/3240508.3240616","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240616","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}