{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T12:30:28Z","timestamp":1770294628839,"version":"3.49.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,24]]},"DOI":"10.1109\/iccvit63928.2024.10872539","type":"proceedings-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:33:35Z","timestamp":1739471615000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["MFP-CNN: Multi-Scale Fusion and Pooling Network for Accurate Scene Classification"],"prefix":"10.1109","author":[{"given":"Wanjing","family":"Xie","sequence":"first","affiliation":[{"name":"University of Central South,Department of Computer Science And Engineering,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjie","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Central South,Department of Computer Science And Engineering,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Adaptive Self-training Framework for Fine-grained Scene Graph Generation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Kim"},{"key":"ref2","first-page":"4548","article-title":"Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving","volume-title":"Proceedings of the 2022 IEEE International Conference on Robotics and Automation (ICRA)","author":"Li"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA46639.2022.9812234","article-title":"Important Object Identification with Semi-Supervised Learning for Autonomous Driving","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191605"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988934"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12758"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12930"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12937"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27965"},{"key":"ref10","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00745"},{"key":"ref15","first-page":"881","article-title":"Channel Attention Networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Bastidas"},{"key":"ref16","first-page":"11534","article-title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","author":"He","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2014.131"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00165"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20053-3_27","article-title":"MaxViT: Multi-Axis Vision Transformer","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Tu"},{"key":"ref22","volume-title":"EfficientNetV2: Smaller Models and Faster Training","author":"Tan","year":"2021"},{"key":"ref23","volume-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Liu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.144"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.319"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2599292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref32","volume-title":"A Discriminative Representation of Convolutional Features for Indoor Scene Recognition","author":"Khan","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","first-page":"212","article-title":"On Modeling Context from Objects with a Long Short-Term Memory for Indoor Scene Recognition","volume-title":"Proceedings of the 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","author":"Laranjeira"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.68"},{"issue":"4","key":"ref37","article-title":"MFP-CNN: Multi-Scale Fusion and Pooling Network for Accurate Scene Classification[J]","volume":"3","author":"Zhang","year":"2024","journal-title":"Authorea Preprints"}],"event":{"name":"2024 2nd International Conference on Computer, Vision and Intelligent Technology (ICCVIT)","location":"Huaibei, China","start":{"date-parts":[[2024,11,24]]},"end":{"date-parts":[[2024,11,27]]}},"container-title":["2024 2nd International Conference on Computer, Vision and Intelligent Technology (ICCVIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10871946\/10872409\/10872539.pdf?arnumber=10872539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T19:51:42Z","timestamp":1740081102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10872539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccvit63928.2024.10872539","relation":{},"subject":[],"published":{"date-parts":[[2024,11,24]]}}}