{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:55:02Z","timestamp":1762325702587,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031396977"},{"type":"electronic","value":"9783031396984"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-39698-4_29","type":"book-chapter","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:02:40Z","timestamp":1692770560000},"page":"426-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["MMExit: Enabling Fast and\u00a0Efficient Multi-modal DNN Inference with\u00a0Adaptive Network Exits"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4372-7851","authenticated-orcid":false,"given":"Xiaofeng","family":"Hou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-2311","authenticated-orcid":false,"given":"Jiacheng","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4106-2759","authenticated-orcid":false,"given":"Xuehan","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6218-4659","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3885-4912","authenticated-orcid":false,"given":"Kwang-Ting","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Akhtar, M.S., Chauhan, D.S., Ghosal, D., Poria, S., Ekbal, A., Bhattacharyya, P.: Multi-task learning for multi-modal emotion recognition and sentiment analysis. In: NAACL-HLT (2019)","DOI":"10.18653\/v1\/N19-1034"},{"key":"29_CR2","unstructured":"Arevalo, J., Solorio, T., Montes-y G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. In: ICLR (2017)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Bach, F.R., Lanckriet, G.R., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: ICML (2004)","DOI":"10.1145\/1015330.1015424"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Bhattacharjee, A., et al.: MIME: adapting a single neural network for multi-task inference with memory-efficient dynamic pruning. In: DAC (2022)","DOI":"10.1145\/3489517.3530473"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Castro, S., Hazarika, D., P\u00e9rez-Rosas, V., Zimmermann, R., Mihalcea, R., Poria, S.: Towards multimodal sarcasm detection (an _obviously_ perfect paper). In: ACL (2019)","DOI":"10.18653\/v1\/P19-1455"},{"key":"29_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-3-030-85665-6_14","volume-title":"Euro-Par 2021: Parallel Processing","author":"K Choi","year":"2021","unstructured":"Choi, K., Yang, H.: A GPU architecture aware fine-grain pruning technique for deep neural networks. In: Sousa, L., Roma, N., Tom\u00e1s, P. (eds.) Euro-Par 2021. LNCS, vol. 12820, pp. 217\u2013231. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85665-6_14"},{"key":"29_CR7","unstructured":"Cui, W., et al.: DVABatch: diversity-aware multi-entry multi-exit batching for efficient processing of DNN services on GPUs. In: USENIX ATC (2022)"},{"key":"29_CR8","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","volume":"44","author":"Y Han","year":"2021","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. TPAMI 44, 7436\u20137456 (2021)","journal-title":"TPAMI"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Hasan, M.K., et al.: Humor knowledge enriched transformer for understanding multimodal humor. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i14.17534"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Hou, X., et al.: Architecting efficient multi-modal AIoT systems. In: ISCA (2023)","DOI":"10.1145\/3579371.3589066"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hou, X., et al.: Characterizing and understanding end-to-end multi-modal neural networks on GPUs. In: IEEE CAL (2022)","DOI":"10.1109\/LCA.2022.3215718"},{"key":"29_CR12","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., van der Maaten, L., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. In: ICLR (2018)"},{"key":"29_CR13","unstructured":"Jayakumar, S.M., et al.: Multiplicative interactions and where to find them. In: ICLR (2020)"},{"key":"29_CR14","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: ICML (2021)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Laskaridis, S., Kouris, A., Lane, N.D.: Adaptive inference through early-exit networks: design, challenges and directions. In: MobiSys (2021)","DOI":"10.1145\/3469116.3470012"},{"key":"29_CR16","unstructured":"Liang, P.P., et al.: MultiBench: multiscale benchmarks for multimodal representation learning. In: NeurIPS (2021)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., Hou, X., Tang, F.: Fine-grained machine teaching with attention modeling. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i03.5642"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.P.: Efficient low-rank multimodal fusion with modality-specific factors. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"29_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-319-16178-5_33","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"N Neverova","year":"2015","unstructured":"Neverova, N., Wolf, C., Taylor, G.W., Nebout, F.: Multi-scale deep learning for gesture detection and localization. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 474\u2013490. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16178-5_33"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Peng, X., Wei, Y., Deng, A., Wang, D., Hu, D.: Balanced multimodal learning via on-the-fly gradient modulation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Pham, H., Liang, P.P., Manzini, T., Morency, L.P., P\u00f3czos, B.: Found in translation: learning robust joint representations by cyclic translations between modalities. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"29_CR22","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1007\/s12559-020-09734-4","volume":"12","author":"S Scardapane","year":"2020","unstructured":"Scardapane, S., Scarpiniti, M., Baccarelli, E., Uncini, A.: Why should we add early exits to neural networks? Cogn. Comput. 12, 954\u2013966 (2020)","journal-title":"Cogn. Comput."},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Sze, V., Chen, Y.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks. In: Synthesis Lectures on Computer Architecture (2020)","DOI":"10.1007\/978-3-031-01766-7"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.T.: BranchyNet: fast inference via early exiting from deep neural networks. In: ICPR (2016)","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"29_CR25","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2016","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. TPAMI 39, 652\u2013663 (2016)","journal-title":"TPAMI"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. In: EMNLP (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"29_CR27","first-page":"478","volume":"14","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Yang, Z., He, X., Deng, L.: Multimodal intelligence: representation learning, information fusion, and applications. JSTSP 14, 478\u2013493 (2020)","journal-title":"JSTSP"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2023: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39698-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:06:41Z","timestamp":1692770801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39698-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031396977","9783031396984"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39698-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","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":"49","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":"30% - 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":"3.98","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":"4","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)"}}]}}