{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:08Z","timestamp":1763192588923,"version":"3.45.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228292","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["SpaRTAN: Spatial Reinforcement Token-based Aggregation Network for Visual Recognition"],"prefix":"10.1109","author":[{"given":"Quan Bi","family":"Pay","sequence":"first","affiliation":[{"name":"Monash University Malaysia,School of Information Technology"}]},{"given":"Vishnu Monn","family":"Baskaran","sequence":"additional","affiliation":[{"name":"Monash University Malaysia,School of Information Technology"}]},{"given":"Junn Yong","family":"Loo","sequence":"additional","affiliation":[{"name":"Monash University Malaysia,School of Information Technology"}]},{"given":"KokSheik","family":"Wong","sequence":"additional","affiliation":[{"name":"Monash University Malaysia,School of Information Technology"}]},{"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref2","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd International Conference on Learning Representations (ICLR 2015)","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"article-title":"Rethinking attention with performers","volume-title":"International Conference on Learning Representations","author":"Choromanski","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"article-title":"More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref17","first-page":"10353","article-title":"Hornet: Efficient high-order spatial interactions with recursive gated convolutions","volume":"35","author":"Rao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Moganet: Multi-order gated aggregation network","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","key":"ref18"},{"key":"ref19","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"article-title":"A game-theoretic taxonomy of visual concepts in dnns","year":"2021","author":"Cheng","key":"ref22"},{"article-title":"Discovering and explaining the representation bottleneck of dnns","volume-title":"International Conference on Learning Representations","author":"Deng","key":"ref23"},{"key":"ref24","article-title":"Towards a unified gametheoretic view of adversarial perturbations and robustness","author":"Ren","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_27"},{"key":"ref26","first-page":"12934","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"International Conference on Learning Representations","author":"Mehta","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref32","first-page":"980","article-title":"Global filter networks for image classification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref34","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"Xiao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"article-title":"Deformable {detr}: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations","author":"Zhu","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"International Conference on Learning Representations","author":"Liu","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228292.pdf?arnumber=11228292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:39:09Z","timestamp":1763192349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228292","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}