{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:24Z","timestamp":1763192004185,"version":"3.45.0"},"reference-count":45,"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"}],"funder":[{"DOI":"10.13039\/501100001779","name":"Monash University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001779","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229177","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":["Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection"],"prefix":"10.1109","author":[{"given":"Quan Bi","family":"Pay","sequence":"first","affiliation":[{"name":"Monash University,School of Information Technology,Malaysia"}]},{"given":"Vishnu","family":"Monn Baskaran","sequence":"additional","affiliation":[{"name":"Monash University,School of Information Technology,Malaysia"}]},{"given":"Junn Yong","family":"Loo","sequence":"additional","affiliation":[{"name":"Monash University,School of Information Technology,Malaysia"}]},{"given":"KokSheik","family":"Wong","sequence":"additional","affiliation":[{"name":"Monash University,School of Information Technology,Malaysia"}]},{"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.171"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093784"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3029901"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMM48946.2020.9141973"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"Zhu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref18","first-page":"37416","article-title":"Rlip: Relational language-image pre-training for human-object interaction detection","volume":"35","author":"Yuan","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.085"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"article-title":"Discovering and explaining the representation bottleneck of dnns","year":"2021","author":"Deng","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331738"},{"key":"ref24","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn60899.2024.10650093"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093580"},{"article-title":"Wavelet convolutional neural networks","year":"2018","author":"Fujieda","key":"ref31"},{"article-title":"Learning-based image compression using convolutional autoencoder and wavelet decomposition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Akyazi","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.187"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3184845"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3265361"},{"key":"ref36","first-page":"19313","article-title":"Light field networks: Neural scene representations with single-evaluation rendering","volume":"34","author":"Sitzmann","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00808"},{"issue":"143-155","key":"ref38","first-page":"18","article-title":"Generalization and network design strategies","volume":"19","author":"LeCun","year":"1989","journal-title":"Connectionism in perspective"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3401450"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","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":"ref42","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_21"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206626"}],"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\/11229177.pdf?arnumber=11229177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:30:04Z","timestamp":1763191804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229177","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}