{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:27:09Z","timestamp":1778758029005,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,23]]},"DOI":"10.1145\/3746467.3801502","type":"proceedings-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:32Z","timestamp":1778756792000},"page":"38-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Multi-Modal Learning for Extreme Long-Tail Fungi Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2669-1209","authenticated-orcid":false,"given":"Sharoon","family":"Sharif","sequence":"first","affiliation":[{"name":"Computer Science, Alabama A&M University, Normal, Alabama, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1054-5277","authenticated-orcid":false,"given":"Inikpi","family":"Egbunu","sequence":"additional","affiliation":[{"name":"Computer Science, Alabama A&M University, Normal, Alabama, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7362-9905","authenticated-orcid":false,"given":"Yujian","family":"Fu","sequence":"additional","affiliation":[{"name":"Computer Science, Alabama A&M University, Normal, Alabama, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1595-0565","authenticated-orcid":false,"given":"Zhigang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, Alabama A&M University, Normal, Alabama, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob Menick, Sebastian Borgeaud, Andrew Brock, Aida Nematzadeh, Sahand Sharifzadeh, Mikolaj Binkowski, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Karen Simonyan. 2022. Flamingo: A Visual Language Model for Few-Shot Learning. In Proceedings of the Advances in Neural Information Processing Systems. New Orleans, LA, USA."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Chen Xu","year":"2021","unstructured":"Xu Chen, Yongquan Yang, Shijie Wang, Shuang Wang, Peng Wang, and Qi Tian. 2021. DRAGON: Dual-Granularity Aggregation for Long-Tailed Visual Recognition. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. Waikoloa, HI, USA, 1\u201310."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Cui Jiequan","year":"2021","unstructured":"Jiequan Cui, Zhisheng Zhong, Shu Liu, Bei Yu, and Jiaya Jia. 2021. Parametric Contrastive Learning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. Montreal, Canada, 715\u2013724."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017197"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Fu Yanwei","year":"2022","unstructured":"Yanwei Fu, Leonid Sigal, Shih-Fu Chang, and Yu-Gang Jiang. 2022. Meta-Prototype Decoupled Training for Long-Tailed Learning. In Proceedings of the Asian Conference on Computer Vision. Macao, China."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Fukui Akira","year":"2016","unstructured":"Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach. 2016. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, TX, USA, 457\u2013468."},{"key":"e_1_3_2_1_8_1","volume-title":"Working Notes of CLEF","author":"CLEF.","year":"2024","unstructured":"FungiCLEF. 2024. Working Notes of CLEF 2024. https:\/\/ceur-ws.org"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Conference and Labs of the Evaluation Forum","author":"Go\u00ebau Herv\u00e9","year":"2023","unstructured":"Herv\u00e9 Go\u00ebau, Pierre Bonnet, and Alexis Joly. 2023. Overview of PlantCLEF 2023: Image-Based Plant Identification at Global Scale. In Proceedings of the Conference and Labs of the Evaluation Forum. Thessaloniki, Greece."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Weinberger. 2017. On Calibration of Modern Neural Networks. In Proceedings of the International Conference on Machine Learning. Sydney, Australia, 1321\u20131330."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1128\/microbiolspec.FUNK-0052-2016"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the International Conference on Learning Representations. Virtual.","author":"Hu Peng","year":"2021","unstructured":"Peng Hu, Xi Peng, Hongyuan Zhu, Liangli Zhen, Jie Lin, Huaibai Yan, and Dezhong Peng. 2021. Learning Multimodal VAEs Through Mutual Supervision. In Proceedings of the International Conference on Learning Representations. Virtual."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Shell Xu","year":"2022","unstructured":"Shell Xu Hu, Da Li, Jan St\u00fchmer, Minyoung Kim, and Timothy Hospedales. 2022. Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA, USA, 9068\u20139077."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jin Yan","year":"2023","unstructured":"Yan Jin, Mengke Li, Yang Lu, Yiu ming Cheung, and Hanzi Wang. 2023. Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, Canada, 23695\u201323704."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the International Conference on Learning Representations. Addis Ababa, Ethiopia.","author":"Kang Bingyi","year":"2020","unstructured":"Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, and Yannis Kalantidis. 2020. Decoupling Representation and Classifier for Long-Tailed Recognition. In Proceedings of the International Conference on Learning Representations. Addis Ababa, Ethiopia."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li Hongyang","year":"2019","unstructured":"Hongyang Li, David Eigen, Samuel Dodge, Matthew Zeiler, and Xiaogang Wang. 2019. Finding Task-Relevant Features for Meta-Learning by Category Traversal. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA, 1\u201310."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-Training with Frozen Image Encoders and Large Language Models. In Proceedings of the International Conference on Machine Learning. Honolulu, HI, USA, 19730\u201319742."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the International Conference on Learning Representations. Virtual.","author":"Menon Aditya Krishna","year":"2021","unstructured":"Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, and Sanjiv Kumar. 2021. Long-Tail Learning via Logit Adjustment. In Proceedings of the International Conference on Learning Representations. Virtual."},{"key":"e_1_3_2_1_20_1","unstructured":"NeurIPS. 2024. Paper Checklist Guidelines. https:\/\/neurips.cc\/public\/guides\/PaperChecklist"},{"key":"e_1_3_2_1_21_1","volume-title":"DINOv2: Learning Robust Visual Features Without Supervision. Transactions on Machine Learning Research","author":"Oquab Maxime","year":"2024","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Herv\u00e9 J\u00e9gou, Julien Mairal, Patrick Labatut, Armand Joulin, and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features Without Supervision. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"FungiTastic: A Multi-Modal Dataset and Benchmark for Fungi Recognition. arXiv preprint arXiv:2408.13632","author":"Picek Luk\u00e1\u0161","year":"2024","unstructured":"Luk\u00e1\u0161 Picek, Milan \u0160ulc, Ji\u0159\u00ed Matas, Jacob Heilmann-Clausen, Thomas L\u00e6ss\u00f8e, and Tobias Fr\u00f8slev. 2024. FungiTastic: A Multi-Modal Dataset and Benchmark for Fungi Recognition. arXiv preprint arXiv:2408.13632 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Picek Luk\u00e1\u0161","year":"2022","unstructured":"Luk\u00e1\u0161 Picek, Milan \u0160ulc, Ji\u0159\u00ed Matas, Thomas Jeppesen, Jacob Heilmann-Clausen, Thomas L\u00e6ss\u00f8e, and Tobias Fr\u00f8slev. 2022. Danish Fungi 2020 - Not Just Another Image Recognition Dataset. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. Waikoloa, HI, USA, 1525\u20131535."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Conference on Machine Learning. Virtual, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models from Natural Language Supervision. In Proceedings of the International Conference on Machine Learning. Virtual, 8748\u20138763."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. Virtual.","author":"Ren Jiawei","year":"2020","unstructured":"Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, and Hongsheng Li. 2020. Balanced Meta-Softmax for Long-Tailed Visual Recognition. In Proceedings of the Advances in Neural Information Processing Systems. Virtual."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical Networks for Few-Shot Learning. In Proceedings of the Advances in Neural Information Processing Systems. Long Beach, CA, USA, 4077\u20134087."},{"key":"e_1_3_2_1_27_1","unstructured":"Species Fungorum. 2024. Species Fungorum. http:\/\/www.speciesfungorum.org"},{"key":"e_1_3_2_1_28_1","volume-title":"David Carlyn, Li Dong, Wasila Dahdul, Charles Stewart, Tanya Berger-Wolf, Wei-Lun Chao, and Yu Su.","author":"Stevens Samuel","year":"2024","unstructured":"Samuel Stevens, Jiaman Wu, Matthew Thompson, Elizabeth Campolongo, Chan Hee Song, David Carlyn, Li Dong, Wasila Dahdul, Charles Stewart, Tanya Berger-Wolf, Wei-Lun Chao, and Yu Su. 2024. BioCLIP: A Vision Foundation Model for the Tree of Life. arXiv preprint arXiv:2311.18803 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Tian Changyao","year":"2022","unstructured":"Changyao Tian, Wenhai Wang, Xizhou Zhu, Xiaogang Wang, Jifeng Dai, and Yu Qiao. 2022. VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition. In Proceedings of the European Conference on Computer Vision. Tel Aviv, Israel, 73\u201391."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang Jiawei","year":"2021","unstructured":"Jiawei Wang, Thomas Lukasiewicz, Xiaolin Hu, Jianfeng Cai, and Zhenguo Li. 2021. Long-Tailed Recognition via Weight Balancing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, 2617\u20132626."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wei Xi","year":"2020","unstructured":"Xi Wei, Tianzhu Zhang, Yan Li, Yongdong Zhang, and Feng Wu. 2020. Multi-Modality Cross Attention Network for Image and Sentence Matching. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA, 10941\u201310950."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wertheimer Davis","year":"2021","unstructured":"Davis Wertheimer, Luming Tang, and Bharath Hariharan. 2021. Few-Shot Classification with Feature Map Reconstruction Networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, 8012\u20138021."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ye Han-Jia","year":"2020","unstructured":"Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, and Fei Sha. 2020. Few-Shot Learning via Saliency-Guided Hallucination of Samples. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA, 770\u2013779."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang Chi","year":"2020","unstructured":"Chi Zhang, Yujun Cai, Guosheng Lin, and Chunhua Shen. 2020. DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA, 12203\u201312213."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Zhang Yifan","year":"2022","unstructured":"Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, and Jiashi Feng. 2022. Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition. In Proceedings of the Advances in Neural Information Processing Systems. New Orleans, LA, USA."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268118"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhao Qihao","year":"2024","unstructured":"Qihao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, and Jun Liu. 2024. LTGC: Long-Tail Recognition via Leveraging LLMs-Driven Generated Content. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhu Jianggang","year":"2022","unstructured":"Jianggang Zhu, Zheng Wang, Jingjing Chen, Yi-Ping Phoebe Chen, and Yu-Gang Jiang. 2022. Balanced Contrastive Learning for Long-Tailed Visual Recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA, USA, 6908\u20136917."}],"event":{"name":"ACMSE 2026: 2026 ACM Southeast Conference","location":"Troy University Troy AL USA","acronym":"ACMSE 2026"},"container-title":["Proceedings of the 2026 ACM Southeast Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746467.3801502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:07:06Z","timestamp":1778756826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746467.3801502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":38,"alternative-id":["10.1145\/3746467.3801502","10.1145\/3746467"],"URL":"https:\/\/doi.org\/10.1145\/3746467.3801502","relation":{},"subject":[],"published":{"date-parts":[[2026,4,23]]},"assertion":[{"value":"2026-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}