{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:53:37Z","timestamp":1785858817585,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000943","name":"Commonwealth Scientific and Industrial Research Organisation","doi-asserted-by":"publisher","award":["R-91559"],"award-info":[{"award-number":["R-91559"]}],"id":[{"id":"10.13039\/501100000943","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612090","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"1768-1778","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8909-8857","authenticated-orcid":false,"given":"Bingqing","family":"Zhang","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5414-8276","authenticated-orcid":false,"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2746-8186","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Adelaide, Adelaide, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9082-3243","authenticated-orcid":false,"given":"Brano","family":"Kusy","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4515-6792","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8160-1796","authenticated-orcid":false,"given":"Jiajun","family":"Liu","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Object Detection in Video with Spatiotemporal Sampling Networks. ArXiv","author":"Bertasius Gedas","year":"2018","unstructured":"Gedas Bertasius, Lorenzo Torresani, and Jianbo Shi. 2018. Object Detection in Video with Spatiotemporal Sampling Networks. ArXiv, Vol. abs\/1803.05549 (2018)."},{"key":"e_1_3_2_1_2_1","volume-title":"Cascade R-CNN: Delving Into High Quality Object Detection. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cai Zhaowei","year":"2017","unstructured":"Zhaowei Cai and Nuno Vasconcelos. 2017. Cascade R-CNN: Delving Into High Quality Object Detection. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017), 6154--6162."},{"key":"e_1_3_2_1_3_1","volume-title":"End-to-End Object Detection with Transformers. ArXiv","author":"Carion Nicolas","year":"2020","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. ArXiv, Vol. abs\/2005.12872 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"Memory Enhanced Global-Local Aggregation for Video Object Detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Yihong","year":"2020","unstructured":"Yihong Chen, Yue Cao, Han Hu, and Liwei Wang. 2020. Memory Enhanced Global-Local Aggregation for Video Object Detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 10334--10343."},{"key":"e_1_3_2_1_5_1","volume-title":"Perceptual Image Quality Assessment with Transformers. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Cheon Manri","year":"2021","unstructured":"Manri Cheon, Sung-Jun Yoon, Byungyeon Kang, and Junwoo Lee. 2021. Perceptual Image Quality Assessment with Transformers. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2021), 433--442."},{"key":"e_1_3_2_1_6_1","unstructured":"MMTracking Contributors. 2020. MMTracking: OpenMMLab video perception toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmtracking."},{"key":"e_1_3_2_1_7_1","volume-title":"DFA: Dynamic Feature Aggregation for Efficient Video Object Detection. ArXiv","author":"Cui Yiming","year":"2022","unstructured":"Yiming Cui. 2022. DFA: Dynamic Feature Aggregation for Efficient Video Object Detection. ArXiv, Vol. abs\/2210.00588 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"TF-Blender: Temporal Feature Blender for Video Object Detection. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Cui Yiming","year":"2021","unstructured":"Yiming Cui, Liqi Yan, Zhiwen Cao, and Dongfang Liu. 2021. TF-Blender: Temporal Feature Blender for Video Object Detection. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021), 8118--8127."},{"key":"e_1_3_2_1_9_1","volume-title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks. ArXiv","author":"Dai Jifeng","year":"2016","unstructured":"Jifeng Dai, Yi Li, Kaiming He, and Jian Sun. 2016. R-FCN: Object Detection via Region-based Fully Convolutional Networks. ArXiv, Vol. abs\/1605.06409 (2016)."},{"key":"e_1_3_2_1_10_1","volume-title":"Object Guided External Memory Network for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Deng Hanming","year":"2019","unstructured":"Hanming Deng, Yang Hua, Tao Song, Zongpu Zhang, Zhengui Xue, Ruhui Ma, Neil Martin Robertson, and Haibing Guan. 2019a. Object Guided External Memory Network for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 6677--6686."},{"key":"e_1_3_2_1_11_1","volume-title":"Relation Distillation Networks for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Deng Jiajun","year":"2019","unstructured":"Jiajun Deng, Yingwei Pan, Ting Yao, Wen gang Zhou, Houqiang Li, and Tao Mei. 2019b. Relation Distillation Networks for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 7022--7031."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099409"},{"key":"e_1_3_2_1_13_1","first-page":"2567","article-title":"Image Quality Assessment: Unifying Structure and Texture Similarity","volume":"44","author":"Ding Keyan","year":"2020","unstructured":"Keyan Ding, Kede Ma, Shiqi Wang, and Eero P. Simoncelli. 2020. Image Quality Assessment: Unifying Structure and Texture Similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44 (2020), 2567--2581.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_14_1","volume-title":"YOLOX: Exceeding YOLO Series in","author":"Ge Zheng","year":"2021","unstructured":"Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. 2021. YOLOX: Exceeding YOLO Series in 2021. arXiv preprint arXiv:2107.08430 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"e_1_3_2_1_17_1","volume-title":"Progressive Sparse Local Attention for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Guo Chaoxu","year":"2019","unstructured":"Chaoxu Guo, Bin Fan, Jie Gu, Q. Zhang, Shiming Xiang, V\u00e9ronique Prinet, and Chunhong Pan. 2019. Progressive Sparse Local Attention for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 3908--3917."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413927"},{"key":"e_1_3_2_1_19_1","volume-title":"Mining Inter-Video Proposal Relations for Video Object Detection. In European Conference on Computer Vision.","author":"Han Mingfei","unstructured":"Mingfei Han, Yali Wang, Xiaojun Chang, and Y. Qiao. 2020a. Mining Inter-Video Proposal Relations for Video Object Detection. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_20_1","volume-title":"BoxMask: Revisiting Bounding Box Supervision for Video Object Detection. 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2022)","author":"Hashmi Khurram Azeem","year":"2022","unstructured":"Khurram Azeem Hashmi, Alain Pagani, Didier Stricker, and Muhammad Zeshan Afzal. 2022a. BoxMask: Revisiting Bounding Box Supervision for Video Object Detection. 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2022), 2029--2039."},{"key":"e_1_3_2_1_21_1","volume-title":"Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection. ArXiv","author":"Hashmi Khurram Azeem","year":"2022","unstructured":"Khurram Azeem Hashmi, Didier Stricker, and Muhammamd Zeshan Afzal. 2022b. Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection. ArXiv, Vol. abs\/2210.02368 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"QueryProp: Object Query Propagation for High-Performance Video Object Detection. ArXiv","author":"He Fei","year":"2022","unstructured":"Fei He, Naiyu Gao, Jian Jia, Xin Zhao, and Kaiqi Huang. 2022. QueryProp: Object Query Propagation for High-Performance Video Object Detection. ArXiv, Vol. abs\/2207.10959 (2022)."},{"key":"e_1_3_2_1_23_1","volume-title":"Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 770--778."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"e_1_3_2_1_25_1","volume-title":"Video Object Detection with Locally-Weighted Deformable Neighbors. In AAAI Conference on Artificial Intelligence.","author":"Jiang Zhengkai","year":"2019","unstructured":"Zhengkai Jiang, Peng Gao, Chaoxu Guo, Qian Zhang, Shiming Xiang, and Chunhong Pan. 2019. Video Object Detection with Locally-Weighted Deformable Neighbors. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_26_1","first-page":"108323","article-title":"Feature Flow","volume":"122","author":"Jin Ruibing","year":"2020","unstructured":"Ruibing Jin, Guosheng Lin, Changyun Wen, Jianliang Wang, and Fayao Liu. 2020. Feature Flow: In-network Feature Flow Estimation for Video Object Detection. Pattern Recognit., Vol. 122 (2020), 108323.","journal-title":"In-network Feature Flow Estimation for Video Object Detection. Pattern Recognit."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Glenn Jocher Alex Stoken Jirka Borovec Nano Code012 Christopher STAN Liu Changyu Laughing tkianai Adam Hogan lorenzomammana yxNONG AlexWang1900 Laurentiu Diaconu Marc wanghaoyang0106 ml5ah Doug Francisco Ingham Frederik Guilhen Hatovix Jake Poznanski Jiacong Fang Lijun Yu changyu98 Mingyu Wang Naman Gupta Osama Akhtar Petr Dvoracek and Prashant Rai. 2020. ultralytics\/yolov5: v3.1 - Bug Fixes and Performance Improvements. https:\/\/doi.org\/10.5281\/zenodo.4154370","DOI":"10.5281\/zenodo.4154370"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413583"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=oMI9PjOb9Jl","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. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=oMI9PjOb9Jl"},{"key":"e_1_3_2_1_30_1","volume-title":"SSD: Single Shot MultiBox Detector. In European Conference on Computer Vision.","author":"Liu W.","unstructured":"W. Liu, Dragomir Anguelov, D. Erhan, Christian Szegedy, Scott E. Reed, Cheng-Yang Fu, and Alexander C. Berg. 2015. SSD: Single Shot MultiBox Detector. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_31_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Luo Hao","year":"2018","unstructured":"Hao Luo, Wenxuan Xie, Xinggang Wang, and Wenjun Zeng. 2018. Detect or Track: Towards Cost-Effective Video Object Detection\/Tracking. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/wacvw50321.2020.9096948"},{"key":"e_1_3_2_1_34_1","volume-title":"YOLOv3: An Incremental Improvement. ArXiv","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. ArXiv, Vol. abs\/1804.02767 (2018)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 3 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_37_1","volume-title":"YOLOV: Making Still Image Object Detectors Great at Video Object Detection. arXiv preprint arXiv:2208.09686","author":"Shi Yuheng","year":"2022","unstructured":"Yuheng Shi, Naiyan Wang, and Xiaojie Guo. 2022. YOLOV: Making Still Image Object Detectors Great at Video Object Detection. arXiv preprint arXiv:2208.09686 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Shvets Mykhailo","year":"2019","unstructured":"Mykhailo Shvets, Wei Liu, and Alexander C. Berg. 2019a. Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 9755--9763."},{"key":"e_1_3_2_1_39_1","volume-title":"Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Shvets Mykhailo","year":"2019","unstructured":"Mykhailo Shvets, Wei Liu, and Alexander C. Berg. 2019b. Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 9755--9763."},{"key":"e_1_3_2_1_40_1","volume-title":"Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Shvets Mykhailo","year":"2019","unstructured":"Mykhailo Shvets, Wei Liu, and Alexander C. Berg. 2019c. Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 9755--9763."},{"key":"e_1_3_2_1_41_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Sun Guanxiong","year":"2020","unstructured":"Guanxiong Sun, Yang Hua, Guosheng Hu, and Neil Martin Robertson. 2020. MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_1"},{"key":"e_1_3_2_1_43_1","volume-title":"Attention is All you Need. ArXiv","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. ArXiv, Vol. abs\/1706.03762 (2017)."},{"key":"e_1_3_2_1_44_1","volume-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696","author":"Wang Chien-Yao","year":"2022","unstructured":"Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_46_1","volume-title":"Sequence Level Semantics Aggregation for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wu Haiping","year":"2019","unstructured":"Haiping Wu, Yuntao Chen, Naiyan Wang, and Zhaoxiang Zhang. 2019. Sequence Level Semantics Aggregation for Video Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 9216--9224."},{"key":"e_1_3_2_1_47_1","volume-title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training. ArXiv","author":"Zhang Hongkai","year":"2020","unstructured":"Hongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, and Xilin Chen. 2020. Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training. ArXiv, Vol. abs\/2004.06002 (2020)."},{"key":"e_1_3_2_1_48_1","volume-title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv: 2203.03605 [cs.CV]","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M. Ni, and Heung-Yeung Shum. 2022. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv: 2203.03605 [cs.CV]"},{"key":"e_1_3_2_1_49_1","volume-title":"TransVOD: End-to-end Video Object Detection with Spatial-Temporal Transformers. arXiv preprint arXiv:2201.05047","author":"Zhou Qianyu","year":"2022","unstructured":"Qianyu Zhou, Xiangtai Li, Lu He, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lizhuang Ma, and Dacheng Tao. 2022. TransVOD: End-to-end Video Object Detection with Spatial-Temporal Transformers. arXiv preprint arXiv:2201.05047 (2022)."},{"key":"e_1_3_2_1_50_1","volume-title":"Towards High Performance Video Object Detection. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhu Xizhou","year":"2017","unstructured":"Xizhou Zhu, Jifeng Dai, Lu Yuan, and Yichen Wei. 2017a. Towards High Performance Video Object Detection. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017), 7210--7218."},{"key":"e_1_3_2_1_51_1","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable DETR: Deformable Transformers for End-to-End Object Detection. arXiv preprint arXiv:2010.04159 (2020)."},{"key":"e_1_3_2_1_52_1","volume-title":"Flow-Guided Feature Aggregation for Video Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV)","author":"Zhu Xizhou","year":"2017","unstructured":"Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, and Yichen Wei. 2017b. Flow-Guided Feature Aggregation for Video Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV) (2017), 408--417."},{"key":"e_1_3_2_1_53_1","volume-title":"Deep Feature Flow for Video Recognition. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhu Xizhou","year":"2016","unstructured":"Xizhou Zhu, Yuwen Xiong, Jifeng Dai, Lu Yuan, and Yichen Wei. 2016. Deep Feature Flow for Video Recognition. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 4141--4150."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612090","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:44Z","timestamp":1755821144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3612090","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612090","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}