{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:56:39Z","timestamp":1740106599767,"version":"3.37.3"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001117","62171134"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1016\/j.jvcir.2023.103903","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T01:16:02Z","timestamp":1690852562000},"page":"103903","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["CCA-FPN: Channel and content adaptive object detection"],"prefix":"10.1016","volume":"95","author":[{"given":"Zhiyang","family":"Ye","sequence":"first","affiliation":[]},{"given":"Chengdong","family":"Lan","sequence":"additional","affiliation":[]},{"given":"Min","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Xu","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Chen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.jvcir.2023.103903_b1","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","article-title":"Deep learning for generic object detection: A survey","volume":"128","author":"Liu","year":"2020","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"10.1016\/j.jvcir.2023.103903_b2","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: A review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"10.1016\/j.jvcir.2023.103903_b3","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.jvcir.2023.103903_b4","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"10.1016\/j.jvcir.2023.103903_b5","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, Ross Girshick, Mask r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2961\u20132969."},{"issue":"5","key":"10.1016\/j.jvcir.2023.103903_b6","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","article-title":"Cascade R-CNN: high quality object detection and instance segmentation","volume":"43","author":"Cai","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2023.103903_b7","series-title":"European Conference on Computer Vision","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.jvcir.2023.103903_b8","doi-asserted-by":"crossref","unstructured":"Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, You only look once: Unified, real-time object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.1016\/j.jvcir.2023.103903_b9","unstructured":"Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Doll\u00e1r, Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980\u20132988."},{"key":"10.1016\/j.jvcir.2023.103903_b10","doi-asserted-by":"crossref","unstructured":"Zhi Tian, Chunhua Shen, Hao Chen, Tong He, Fcos: Fully convolutional one-stage object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10.1016\/j.jvcir.2023.103903_b11","unstructured":"Tsung-Yi Lin, Piotr Doll\u00e1r, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117\u20132125."},{"key":"10.1016\/j.jvcir.2023.103903_b12","doi-asserted-by":"crossref","unstructured":"Jiangmiao Pang, Kai Chen, Jianping Shi, Huajun Feng, Wanli Ouyang, Dahua Lin, Libra r-cnn: Towards balanced learning for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 821\u2013830.","DOI":"10.1109\/CVPR.2019.00091"},{"key":"10.1016\/j.jvcir.2023.103903_b13","first-page":"1","article-title":"CE-FPN: enhancing channel information for object detection","author":"Luo","year":"2022","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.jvcir.2023.103903_b14","doi-asserted-by":"crossref","unstructured":"Siyuan Qiao, Liang-Chieh Chen, Alan Yuille, Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10213\u201310224.","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"10.1016\/j.jvcir.2023.103903_b15","unstructured":"Chaoxu Guo, Bin Fan, Qian Zhang, Shiming Xiang, Chunhong Pan, Augfpn: Improving multi-scale feature learning for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12595\u201312604."},{"year":"2020","series-title":"Attention-guided context feature pyramid network for object detection","author":"Cao","key":"10.1016\/j.jvcir.2023.103903_b16"},{"year":"2015","series-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","key":"10.1016\/j.jvcir.2023.103903_b17"},{"key":"10.1016\/j.jvcir.2023.103903_b18","article-title":"Dynamic filter networks","volume":"29","author":"Jia","year":"2016","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"10.1016\/j.jvcir.2023.103903_b19","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.jvcir.2023.103903_b20","unstructured":"Xingxing Xie, Gong Cheng, Jiabao Wang, Xiwen Yao, Junwei Han, Oriented R-CNN for object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 3520\u20133529."},{"key":"10.1016\/j.jvcir.2023.103903_b21","first-page":"1","article-title":"Dual-aligned oriented detector","volume":"60","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2023.103903_b22","first-page":"1","article-title":"Anchor-free oriented proposal generator for object detection","volume":"60","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"year":"2018","series-title":"Yolov3: An incremental improvement","author":"Redmon","key":"10.1016\/j.jvcir.2023.103903_b23"},{"key":"10.1016\/j.jvcir.2023.103903_b24","doi-asserted-by":"crossref","unstructured":"Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z Li, Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9759\u20139768.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"10.1016\/j.jvcir.2023.103903_b25","doi-asserted-by":"crossref","unstructured":"Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, Jiaya Jia, Path aggregation network for instance segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8759\u20138768.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"10.1016\/j.jvcir.2023.103903_b26","doi-asserted-by":"crossref","unstructured":"Sean Bell, C Lawrence Zitnick, Kavita Bala, Ross Girshick, Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2874\u20132883.","DOI":"10.1109\/CVPR.2016.314"},{"key":"10.1016\/j.jvcir.2023.103903_b27","doi-asserted-by":"crossref","unstructured":"Zhe Chen, Shaoli Huang, Dacheng Tao, Context refinement for object detection, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 71\u201386.","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"10.1016\/j.jvcir.2023.103903_b28","doi-asserted-by":"crossref","unstructured":"Han Hu, Jiayuan Gu, Zheng Zhang, Jifeng Dai, Yichen Wei, Relation networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3588\u20133597.","DOI":"10.1109\/CVPR.2018.00378"},{"key":"10.1016\/j.jvcir.2023.103903_b29","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778."},{"key":"10.1016\/j.jvcir.2023.103903_b30","doi-asserted-by":"crossref","unstructured":"Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei, Deformable convolutional networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"10.1016\/j.jvcir.2023.103903_b31","doi-asserted-by":"crossref","first-page":"3637","DOI":"10.1007\/s00521-020-05217-7","article-title":"Scale-aware feature pyramid architecture for marine object detection","volume":"33","author":"Xu","year":"2021","journal-title":"Neural Comput. Appl."},{"year":"2019","series-title":"Spatial group-wise enhance: Improving semantic feature learning in convolutional networks","author":"Li","key":"10.1016\/j.jvcir.2023.103903_b32"},{"year":"2019","series-title":"Learning spatial fusion for single-shot object detection","author":"Liu","key":"10.1016\/j.jvcir.2023.103903_b33"},{"issue":"17","key":"10.1016\/j.jvcir.2023.103903_b34","doi-asserted-by":"crossref","first-page":"14881","DOI":"10.1007\/s00521-022-07264-8","article-title":"Refined marine object detector with attention-based spatial pyramid pooling networks and bidirectional feature fusion strategy","volume":"34","author":"Xu","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.jvcir.2023.103903_b35","doi-asserted-by":"crossref","unstructured":"Jie Hu, Li Shen, Gang Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"year":"2018","series-title":"Bam: Bottleneck attention module","author":"Park","key":"10.1016\/j.jvcir.2023.103903_b36"},{"key":"10.1016\/j.jvcir.2023.103903_b37","doi-asserted-by":"crossref","unstructured":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon, Cbam: Convolutional block attention module, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.jvcir.2023.103903_b38","unstructured":"Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang, Selective kernel networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 510\u2013519."},{"key":"10.1016\/j.jvcir.2023.103903_b39","doi-asserted-by":"crossref","unstructured":"Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He, Non-local neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10.1016\/j.jvcir.2023.103903_b40","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"10.1016\/j.jvcir.2023.103903_b41","doi-asserted-by":"crossref","unstructured":"Zhen Zhu, Mengde Xu, Song Bai, Tengteng Huang, Xiang Bai, Asymmetric non-local neural networks for semantic segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 593\u2013602.","DOI":"10.1109\/ICCV.2019.00068"},{"key":"10.1016\/j.jvcir.2023.103903_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2020.103609","article-title":"Purifying real images with an attention-guided style transfer network for gaze estimation","volume":"91","author":"Fu","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"year":"2017","series-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","key":"10.1016\/j.jvcir.2023.103903_b43"},{"key":"10.1016\/j.jvcir.2023.103903_b44","doi-asserted-by":"crossref","unstructured":"Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen, Mobilenetv2: Inverted residuals and linear bottlenecks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.jvcir.2023.103903_b45","unstructured":"Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun, Shufflenet v2: Practical guidelines for efficient cnn architecture design, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 116\u2013131."},{"key":"10.1016\/j.jvcir.2023.103903_b46","series-title":"International Conference on Machine Learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.jvcir.2023.103903_b47","doi-asserted-by":"crossref","unstructured":"Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu, Dual attention network for scene segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"10.1016\/j.jvcir.2023.103903_b48","series-title":"International Conference on Machine Learning","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"Zhang","year":"2019"},{"year":"2020","series-title":"Delving deeper into anti-aliasing in convnets","author":"Zou","key":"10.1016\/j.jvcir.2023.103903_b49"},{"year":"2020","series-title":"International conference on machine learning","author":"Jin","key":"10.1016\/j.jvcir.2023.103903_b50"},{"key":"10.1016\/j.jvcir.2023.103903_b51","series-title":"Proc. Icml","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"Maas","year":"2013"},{"year":"2019","series-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","key":"10.1016\/j.jvcir.2023.103903_b52"},{"key":"10.1016\/j.jvcir.2023.103903_b53","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"year":"2018","series-title":"Detectron","author":"Girshick","key":"10.1016\/j.jvcir.2023.103903_b54"},{"year":"2017","series-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","key":"10.1016\/j.jvcir.2023.103903_b55"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320323001530?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320323001530?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T03:37:28Z","timestamp":1715225848000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320323001530"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":55,"alternative-id":["S1047320323001530"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2023.103903","relation":{},"ISSN":["1047-3203"],"issn-type":[{"type":"print","value":"1047-3203"}],"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CCA-FPN: Channel and content adaptive object detection","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2023.103903","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"103903"}}