{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:48:18Z","timestamp":1750308498508,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T00:00:00Z","timestamp":1736985600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,16]]},"DOI":"10.1145\/3722150.3722159","type":"proceedings-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T10:37:39Z","timestamp":1747132659000},"page":"53-58","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DenseDetect: Exploring End-to-End Human Detection Models for Dense and Occluded Scenes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8954-9586","authenticated-orcid":false,"given":"ZIANG","family":"LI","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3528-4739","authenticated-orcid":false,"given":"Kan","family":"LI","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4237-1961","authenticated-orcid":false,"given":"SHAOJIE","family":"QU","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"e_1_3_3_1_1_2","volume-title":"FCOS: Fully Convolutional One-Stage Object Detection. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV. 9626\u20139635","author":"Tian Zhi","year":"2019","unstructured":"Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2019. FCOS: Fully Convolutional One-Stage Object Detection. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV. 9626\u20139635."},{"key":"e_1_3_3_1_2_2","volume-title":"Objects as points. CoRR abs\/1904.07850","author":"Zhou Xingyi","year":"2019","unstructured":"Xingyi Zhou, Dequan Wang, and Philipp Kr\u00e4henb\u00fchl. 2019. Objects as points. CoRR abs\/1904.07850 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_3_2","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_3_1_4_2","volume-title":"Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 580\u2013587","author":"Girshick Ross B.","year":"2014","unstructured":"Ross B. Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2014. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 580\u2013587."},{"key":"e_1_3_3_1_5_2","volume-title":"Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. IEEE Computer Society, 779\u2013788","author":"Redmon Joseph","year":"2016","unstructured":"Joseph Redmon, Santosh K. Divvala, Ross Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. IEEE Computer Society, 779\u2013788."},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_6_2","DOI":"10.1609\/aaai.v34i07.6691"},{"key":"e_1_3_3_1_7_2","volume-title":"Double Anchor R-CNN for Human Detection in a Crowd. CoRR abs\/1909.09998","author":"Zhang Kevin","year":"2019","unstructured":"Kevin Zhang, Xiong Feng, Peize Sun, Hu Li, Boxun Li, and Gang Yu. 2019. Double Anchor R-CNN for Human Detection in a Crowd. CoRR abs\/1909.09998 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_8_2","DOI":"10.1109\/CVPR.2019.00662"},{"unstructured":"Yanghao Li Hanzi Mao Ross Girshick and Kaiming He. 2022. Exploring Plain Vision Transformer Backbones for Object Detection. CoRR abs\/2203.16527. arXiv:2203.16527","key":"e_1_3_3_1_9_2"},{"key":"e_1_3_3_1_10_2","volume-title":"Multiple Predictions. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 12211\u201312220","author":"Chu Xuangeng","year":"2020","unstructured":"Xuangeng Chu, Anlin Zheng, Xiangyu Zhang, and Jian Sun. 2020. Detection in Crowded Scenes: One Proposal, Multiple Predictions. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 12211\u201312220."},{"key":"e_1_3_3_1_11_2","volume-title":"Berg","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector, In Computer Vision - ECCV. european conference on computer vision 9905, 21\u201337."},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_12_2","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_13_2","DOI":"10.1109\/TPAMI.2016.2577031"},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_14_2","DOI":"10.1007\/s11263-019-01204-1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_15_2","DOI":"10.1109\/CVPR46437.2021.01422"},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_16_2","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_1_17_2","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 5998\u20136008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_3_1_18_2","volume-title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR. CoRR abs\/2201.12329","author":"Liu Shilong","year":"2022","unstructured":"Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, and Lei Zhang. 2022. DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR. CoRR abs\/2201.12329 (2022)."},{"key":"e_1_3_3_1_19_2","volume-title":"Conditional DETR for Fast Training Convergence. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV. IEEE, 3631\u20133640","author":"Meng Depu","year":"2021","unstructured":"Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, and Jingdong Wang. 2021. Conditional DETR for Fast Training Convergence. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV. IEEE, 3631\u20133640."},{"key":"e_1_3_3_1_20_2","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In 9th International Conference on Learning Representations, ICLR.","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In 9th International Conference on Learning Representations, ICLR."},{"unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024).","key":"e_1_3_3_1_21_2"},{"unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang Zhenda Xie Yu Wu Kai Hu Jiawei Wang Yaofeng Sun Yukun Li Yishi Piao Kang Guan Aixin Liu Xin Xie Yuxiang You Kai Dong Xingkai Yu Haowei Zhang Liang Zhao Yisong Wang and Chong Ruan. 2024. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding. arXiv:2412.10302 [cs.CV] https:\/\/arxiv.org\/abs\/2412.10302","key":"e_1_3_3_1_22_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_23_2","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_24_2","volume-title":"Feature Pyramid Networks for Object Detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 936\u2013944","author":"Lin Tsung-Yi","year":"2017","unstructured":"Tsung-Yi Lin, Piotr Doll\u00e1r, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2017. Feature Pyramid Networks for Object Detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 936\u2013944."},{"key":"e_1_3_3_1_25_2","volume-title":"Dynamic Filter Networks. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems. 667\u2013675","author":"Jia Xu","year":"2016","unstructured":"Xu Jia, Bert De Brabandere, Tinne Tuytelaars, and Luc Van Gool. 2016. Dynamic Filter Networks. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems. 667\u2013675."},{"doi-asserted-by":"publisher","key":"e_1_3_3_1_26_2","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_3_1_27_2","volume-title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd. CoRR abs\/1805.00123","author":"Shao Shuai","year":"2018","unstructured":"Shuai Shao, Zijian Zhao, Boxun Li, Tete Xiao, Gang Yu, Xiangyu Zhang, and Jian Sun. 2018. CrowdHuman: A Benchmark for Detecting Human in a Crowd. CoRR abs\/1805.00123 (2018)."},{"key":"e_1_3_3_1_28_2","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR."},{"unstructured":"Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2.","key":"e_1_3_3_1_29_2"},{"key":"e_1_3_3_1_30_2","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS, Vol. 9. 249\u2013256."}],"event":{"acronym":"CCEAI 2025","name":"CCEAI 2025: 2025 9th International Conference on Control Engineering and Artificial Intelligence","location":"Ho Chi Minh City Vietnam"},"container-title":["Proceedings of the 2025 9th International Conference on Control Engineering and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722150.3722159","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3722150.3722159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:43:50Z","timestamp":1750272230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722150.3722159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,16]]},"references-count":30,"alternative-id":["10.1145\/3722150.3722159","10.1145\/3722150"],"URL":"https:\/\/doi.org\/10.1145\/3722150.3722159","relation":{},"subject":[],"published":{"date-parts":[[2025,1,16]]},"assertion":[{"value":"2025-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}