{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:58Z","timestamp":1781538958097,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"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":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810715","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1716-1720","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An Energy-Efficient Multimodal Retrieval Framework for Inference on Heterogeneous Edge Nodes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0960-2798","authenticated-orcid":false,"given":"Junfeng","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer Science , Shanghai Jiao Tong University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2428-9211","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9656-2774","authenticated-orcid":false,"given":"Mingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1654-121X","authenticated-orcid":false,"given":"Zhaoxi","family":"Feng","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9349-545X","authenticated-orcid":false,"given":"Manzhou","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7794-3185","authenticated-orcid":false,"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"China Agricultural University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Mohammad\u00a0Mahdi Abootorabi Amirhosein Zobeiri Mahdi Dehghani Mohammadali Mohammadkhani Bardia Mohammadi Omid Ghahroodi Mahdieh Soleymani\u00a0Baghshah and Ehsaneddin Asgari. 2025. Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.08826 (2025). arxiv:https:\/\/arXiv.org\/abs\/2502.08826\u00a0[cs.IR]","DOI":"10.18653\/v1\/2025.findings-acl.861"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00135"},{"key":"e_1_3_3_1_4_2","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","author":"Chen Jinqian","year":"2024","unstructured":"Jinqian Chen, Haoyu Tang, Junhao Cheng, Ming Yan, Ji Zhang, Mingzhu Xu, Yupeng Hu, and Liqiang Nie. 2024. Breaking Barriers of System Heterogeneity: Straggler-Tolerant Multimodal Federated Learning via Knowledge Distillation. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)."},{"key":"e_1_3_3_1_5_2","unstructured":"Xinlei Chen Hao Fang Tsung-Yi Lin Ramakrishna Vedantam Saurabh Gupta Piotr Doll\u00e1r and C\u00a0Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1504.00325 (2015)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Du Dandan Yu Kaidi Yu Dongyu Zhi Jinyi Wang Yun and Chunhui Jing. 2025. The Impact of Task Difficulty Environmental Color Complexity and Teaching Models on AR-Assisted Subway Maintenance Training. International Journal of Human\u2013Computer Interaction (2025) 1\u201314.","DOI":"10.1080\/10447318.2024.2443266"},{"key":"e_1_3_3_1_7_2","unstructured":"Baoxia Du Hongyang Du Dusit Niyato and Ruidong Li. 2025. Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks. IEEE Transactions on Mobile Computing (2025)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Duoduo Feng Xiangteng He and Yuxin Peng. 2023. MKVSE: Multimodal Knowledge Enhanced Visual-Semantic Embedding for Image-Text Retrieval. ACM Transactions on Multimedia Computing Communications and Applications 19 5 (2023) 1\u201321.","DOI":"10.1145\/3580501"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Yang He and Lingao Xiao. 2023. Structured pruning for deep convolutional neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence 46 5 (2023) 2900\u20132919.","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Zhong Ji Kexin Chen Yuqing He Yanwei Pang and Xuelong Li. 2022. Heterogeneous Memory Enhanced Graph Reasoning Network for Cross-Modal Retrieval. Science China Information Sciences 65 7 (2022) 172104.","DOI":"10.1007\/s11432-021-3367-y"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_3_1_12_2","unstructured":"Xiaotang Jiang Huan Wang Yiliu Chen Ziqi Wu Lichuan Wang Bin Zou Yafeng Yang Zongyang Cui Yu Cai Tianhang Yu et\u00a0al. 2020. MNN: A universal and efficient inference engine. Proceedings of Machine Learning and Systems 2 (2020) 1\u201313."},{"key":"e_1_3_3_1_13_2","unstructured":"Alexander\u00a0Htet Kyaw Haotian Ma Sasa Zivkovic and Jenny Sabin. 2025. AI Assisted AR Assembly: Object Recognition and Computer Vision for Augmented Reality Assisted Assembly. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.05394 (2025)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Weizhe Lin Jinghong Chen Jingbiao Mei Alexandru Coca and Bill Byrne. 2023. Fine-Grained Late-Interaction Multi-Modal Retrieval for Retrieval Augmented Visual Question Answering. Advances in Neural Information Processing Systems 36 (2023) 22820\u201322840.","DOI":"10.52202\/075280-0990"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754761"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29837"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Xin Nie Laurence\u00a0T Yang Zhe Li Fulan Fan and Zecan Yang. 2025. Tensor-empowered Incomplete Multimodal Learning with Modality Reconstruction for Edge Intelligence. ACM Transactions on Multimedia Computing Communications and Applications (2025).","DOI":"10.1145\/3712593"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Babak Rokh Ali Azarpeyvand and Alireza Khanteymoori. 2023. A comprehensive survey on model quantization for deep neural networks in image classification. ACM Transactions on Intelligent Systems and Technology 14 6 (2023) 1\u201350.","DOI":"10.1145\/3623402"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Yan Sun Yinqiu Liu Shaoyong Guo Xuesong Qiu Jiewei Chen Jiakai Hao and Dusit Niyato. 2025. Edge Large AI Model Agent-Empowered Cognitive Multimodal Semantic Communication. IEEE Transactions on Mobile Computing (2025).","DOI":"10.1109\/ICC52391.2025.11161296"},{"key":"e_1_3_3_1_22_2","first-page":"387","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Wei Cong","year":"2024","unstructured":"Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang, Jie Fu, Alan Ritter, and Wenhu Chen. 2024. UniIR: Training and Benchmarking Universal Multimodal Information Retrievers. In Proceedings of the European Conference on Computer Vision. Springer Nature Switzerland, Cham, 387\u2013404."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW63119.2024.00045"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560545"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755868"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26309"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750472"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.935"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Lei Zhu Chaoqun Zheng Weili Guan Jingjing Li Yang Yang and Heng\u00a0Tao Shen. 2023. Multi-Modal Hashing for Efficient Multimedia Retrieval: A Survey. IEEE Transactions on Knowledge and Data Engineering 36 1 (2023) 239\u2013260.","DOI":"10.1109\/TKDE.2023.3282921"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:22:28Z","timestamp":1781536948000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810715"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":29,"alternative-id":["10.1145\/3805622.3810715","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810715","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}