{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T04:59:19Z","timestamp":1783832359111,"version":"3.55.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729720","type":"print"},{"value":"9783031729737","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72973-7_8","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"124-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":177,"title":["Agent Attention: On the\u00a0Integration of\u00a0Softmax and\u00a0Linear Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3431-6189","authenticated-orcid":false,"given":"Dongchen","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9772-4768","authenticated-orcid":false,"given":"Tianzhu","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5706-8784","authenticated-orcid":false,"given":"Yizeng","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7965-364X","authenticated-orcid":false,"given":"Zhuofan","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4426-8706","authenticated-orcid":false,"given":"Siyuan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-9283","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"8_CR1","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: ICLR (2023)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Hoffman, J.: Hydra attention: efficient attention with many heads. In: ECCVW (2022)","DOI":"10.1007\/978-3-031-25082-8_3"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: CVPRW (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"8_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58452-8_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Birdal, T., Lenssen, J.E., Menegatti, E., Guibas, L., Tombari, F.: Quaternion equivariant capsule networks for 3D point clouds. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 1\u201319. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_1"},{"key":"8_CR6","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"8_CR7","unstructured":"Choromanski, K., et\u00a0al.: Rethinking attention with performers. In: ICLR (2021)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"8_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Han, D., Pan, X., Han, Y., Song, S., Huang, G.: Flatten transformer: Vision transformer using focused linear attention. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Han, Y., et al.: Dynamic perceiver for efficient visual recognition. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00551"},{"key":"8_CR13","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. TPAMI (2021)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Han, Y., et al.: Latency-aware unified dynamic networks for efficient image recognition. TPAMI (2024)","DOI":"10.1109\/TPAMI.2024.3393530"},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Han, Y., et al.: Learning to weight samples for dynamic early-exiting networks. In: ECCV (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_22","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Hassani, A., Walton, S., Li, J., Li, S., Shi, H.: Neighborhood attention transformer. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"8_CR18","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are rnns: fast autoregressive transformers with linear attention. In: ICML (2020)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: improved multiscale vision transformers for classification and detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Efficient and explicit modelling of image hierarchies for image restoration. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"8_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"8_CR26","unstructured":"Lu, J., et al.: Soft: Softmax-free transformer with linear complexity. In: NeurIPS (2021)"},{"key":"8_CR27","unstructured":"Pan, X., Ye, T., Han, D., Song, S., Huang, G.: Contrastive language-image pre-training with knowledge graphs. In: NeurIPS (2022)"},{"key":"8_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: ACL (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"8_CR33","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: attention with linear complexities. In: WACV (2021)"},{"key":"8_CR34","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"8_CR35","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"8_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pvt v2: improved baselines with pyramid vision transformer. Comput. Visual Media (2022)","DOI":"10.1007\/s41095-022-0274-8"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Cvt: introducing convolutions to vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Xia, Z., Han, D., Han, Y., Pan, X., Song, S., Huang, G.: Gsva: generalized segmentation via multimodal large language models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"8_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"8_CR43","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. In: NeurIPS (2021)"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Nystr\u00f6mformer: A nystr\u00f6m-based algorithm for approximating self-attention. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"8_CR45","unstructured":"Yan, H., Li, Z., Li, W., Wang, C., Wu, M., Zhang, C.: Contnet: Why not use convolution and transformer at the same time? arXiv preprint arXiv:2104.13497 (2021)"},{"key":"8_CR46","unstructured":"Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. In: NeurIPS (2021)"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"You, H., et al.: Castling-vit: compressing self-attention via switching towards linear-angular attention at vision transformer inference. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01387"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. IJCV (2019)","DOI":"10.1007\/s11263-018-1140-0"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.: Biformer: vision transformer with bi-level routing attention. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00995"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72973-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T15:00:37Z","timestamp":1739631637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72973-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031729720","9783031729737"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72973-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}