{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T13:19:01Z","timestamp":1784812741812,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61836011"],"award-info":[{"award-number":["61836011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350978","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"629-637","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Long Short-Term Relation Networks for Video Action Detection"],"prefix":"10.1145","author":[{"given":"Dong","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China & JD AI Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & JD AI Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaofan","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & JD AI Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & JD AI Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & JD AI Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jo ao Carreira and Andrew Zisserman. 2017. Quo vadis action recognition? a new model and the kinetics dataset. In CVPR .  Jo ao Carreira and Andrew Zisserman. 2017. Quo vadis action recognition? a new model and the kinetics dataset. In CVPR .","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jiajun Deng Yingwei Pan Ting Yao Wengang Zhou Houqiang Li and Tao Mei. 2019. Relation Distillation Networks for Video Object Detection. In ICCV .  Jiajun Deng Yingwei Pan Ting Yao Wengang Zhou Houqiang Li and Tao Mei. 2019. Relation Distillation Networks for Video Object Detection. In ICCV .","DOI":"10.1109\/ICCV.2019.00712"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer Axel Pinz and Andrew Zisserman. 2017. Detect to track and track to detect. In ICCV .  Christoph Feichtenhofer Axel Pinz and Andrew Zisserman. 2017. Detect to track and track to detect. In ICCV .","DOI":"10.1109\/ICCV.2017.330"},{"key":"e_1_3_2_1_4_1","volume-title":"Carl Doersch, and Andrew Zisserman.","author":"Girdhar Rohit","year":"2019"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Ross Girshick. 2015. Fast r-cnn. In ICCV .  Ross Girshick. 2015. Fast r-cnn. In ICCV .","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Georgia Gkioxari Ross Girshick Piotr Doll\u00e1r and Kaiming He. 2018. Detecting and recognizing human-object interactions. In CVPR .  Georgia Gkioxari Ross Girshick Piotr Doll\u00e1r and Kaiming He. 2018. Detecting and recognizing human-object interactions. In CVPR .","DOI":"10.1109\/CVPR.2018.00872"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Georgia Gkioxari and Jitendra Malik. 2015. Finding action tubes. In CVPR .  Georgia Gkioxari and Jitendra Malik. 2015. Finding action tubes. In CVPR .","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"e_1_3_2_1_8_1","volume-title":"et almbox","author":"Gu Chunhui","year":"2018"},{"key":"e_1_3_2_1_9_1","volume-title":"Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S Huang.","author":"Han Wei","year":"2016"},{"key":"e_1_3_2_1_10_1","unstructured":"Jiawei He Mostafa S Ibrahim Zhiwei Deng and Greg Mori. 2018. Generic Tubelet Proposals for Action Localization. In WACV .  Jiawei He Mostafa S Ibrahim Zhiwei Deng and Greg Mori. 2018. Generic Tubelet Proposals for Action Localization. In WACV ."},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR .  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR ."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Rui Hou Chen Chen and Mubarak Shah. 2017. Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos. In ICCV .  Rui Hou Chen Chen and Mubarak Shah. 2017. Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos. In ICCV .","DOI":"10.1109\/ICCV.2017.620"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Han Hu Jiayuan Gu Zheng Zhang Jifeng Dai and Yichen Wei. 2018. Relation networks for object detection. In CVPR .  Han Hu Jiayuan Gu Zheng Zhang Jifeng Dai and Yichen Wei. 2018. Relation networks for object detection. In CVPR .","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Hueihan Jhuang Juergen Gall Silvia Zuffi Cordelia Schmid and Michael J Black. 2013. Towards understanding action recognition. In ICCV .  Hueihan Jhuang Juergen Gall Silvia Zuffi Cordelia Schmid and Michael J Black. 2013. Towards understanding action recognition. In ICCV .","DOI":"10.1109\/ICCV.2013.396"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_16_1","volume-title":"Human Centric Spatio-Temporal Action Localization. In ActivityNet Workshop on CVPR .","author":"Jianwen"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Vicky Kalogeiton Philippe Weinzaepfel Vittorio Ferrari and Cordelia Schmid. 2017. Action tubelet detector for spatio-temporal action localization. In ICCV .  Vicky Kalogeiton Philippe Weinzaepfel Vittorio Ferrari and Cordelia Schmid. 2017. Action tubelet detector for spatio-temporal action localization. In ICCV .","DOI":"10.1109\/ICCV.2017.472"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Kai Kang Hongsheng Li Tong Xiao Wanli Ouyang Junjie Yan Xihui Liu and Xiaogang Wang. 2017. Object detection in videos with tubelet proposal networks. In CVPR .  Kai Kang Hongsheng Li Tong Xiao Wanli Ouyang Junjie Yan Xihui Liu and Xiaogang Wang. 2017. Object detection in videos with tubelet proposal networks. In CVPR .","DOI":"10.1109\/CVPR.2017.101"},{"key":"e_1_3_2_1_19_1","volume-title":"T-cnn: Tubelets with convolutional neural networks for object detection from videos","author":"Kang Kai","year":"2018"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Andrej Karpathy George Toderici Sanketh Shetty Thomas Leung Rahul Sukthankar and Li Fei-Fei. 2014. Large-scale video classification with convolutional neural networks. In CVPR .  Andrej Karpathy George Toderici Sanketh Shetty Thomas Leung Rahul Sukthankar and Li Fei-Fei. 2014. Large-scale video classification with convolutional neural networks. In CVPR .","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_21_1","unstructured":"Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR .  Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR ."},{"key":"e_1_3_2_1_22_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In NIPS .  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In NIPS ."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Tian Lan Yang Wang and Greg Mori. 2011. Discriminative figure-centric models for joint action localization and recognition. In ICCV .  Tian Lan Yang Wang and Greg Mori. 2011. Discriminative figure-centric models for joint action localization and recognition. In ICCV .","DOI":"10.1109\/ICCV.2011.6126472"},{"key":"e_1_3_2_1_24_1","unstructured":"Dong Li Zhaofan Qiu Qi Dai Ting Yao and Tao Mei. 2018a. Recurrent tubelet proposal and recognition networks for action detection. In ECCV .  Dong Li Zhaofan Qiu Qi Dai Ting Yao and Tao Mei. 2018a. Recurrent tubelet proposal and recognition networks for action detection. In ECCV ."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"e_1_3_2_1_26_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. In ICLR .","author":"Loshchilov Ilya","year":"2017"},{"key":"e_1_3_2_1_27_1","unstructured":"Chih-Yao Ma Asim Kadav Iain Melvin Zsolt Kira Ghassan AlRegib and Hans Peter Graf. 2018. Attend and interact: Higher-order object interactions for video understanding. In CVPR .  Chih-Yao Ma Asim Kadav Iain Melvin Zsolt Kira Ghassan AlRegib and Hans Peter Graf. 2018. Attend and interact: Higher-order object interactions for video understanding. In CVPR ."},{"key":"e_1_3_2_1_28_1","unstructured":"Xiaojiang Peng and Cordelia Schmid. 2016. Multi-region two-stream R-CNN for action detection. In ECCV .  Xiaojiang Peng and Cordelia Schmid. 2016. Multi-region two-stream R-CNN for action detection. In ECCV ."},{"key":"e_1_3_2_1_29_1","unstructured":"Siyuan Qi Wenguan Wang Baoxiong Jia Jianbing Shen and Song-Chun Zhu. 2018. Learning human-object interactions by graph parsing neural networks. In ECCV .  Siyuan Qi Wenguan Wang Baoxiong Jia Jianbing Shen and Song-Chun Zhu. 2018. Learning human-object interactions by graph parsing neural networks. In ECCV ."},{"key":"e_1_3_2_1_30_1","unstructured":"Zhaofan Qiu Ting Yao and Tao Mei. 2017a. Deep quantization: Encoding convolutional activations with deep generative model. In CVPR .  Zhaofan Qiu Ting Yao and Tao Mei. 2017a. Deep quantization: Encoding convolutional activations with deep generative model. In CVPR ."},{"key":"e_1_3_2_1_31_1","unstructured":"Zhaofan Qiu Ting Yao and Tao Mei. 2017b. Learning spatio-temporal representation with pseudo-3d residual networks. In ICCV .  Zhaofan Qiu Ting Yao and Tao Mei. 2017b. Learning spatio-temporal representation with pseudo-3d residual networks. In ICCV ."},{"key":"e_1_3_2_1_32_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS .  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS ."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Mikel D Rodriguez Javed Ahmed and Mubarak Shah. 2008. Action mach a spatio-temporal maximum average correlation height filter for action recognition. In CVPR .  Mikel D Rodriguez Javed Ahmed and Mubarak Shah. 2008. Action mach a spatio-temporal maximum average correlation height filter for action recognition. In CVPR .","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"e_1_3_2_1_34_1","volume-title":"et almbox","author":"Russakovsky Olga","year":"2015"},{"key":"e_1_3_2_1_35_1","volume-title":"Philip HS Torr, and Fabio Cuzzolin","author":"Saha Suman","year":"2016"},{"key":"e_1_3_2_1_36_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In NIPS .  Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In NIPS ."},{"key":"e_1_3_2_1_37_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR .  Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR ."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Gurkirt Singh Suman Saha and Fabio Cuzzolin. 2017. Online real time multiple spatiotemporal action localisation and prediction. In ICCV .  Gurkirt Singh Suman Saha and Fabio Cuzzolin. 2017. Online real time multiple spatiotemporal action localisation and prediction. In ICCV .","DOI":"10.1109\/ICCV.2017.393"},{"key":"e_1_3_2_1_39_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Chen Sun Abhinav Shrivastava Carl Vondrick Kevin Murphy Rahul Sukthankar and Cordelia Schmid. 2018. Actor-centric relation network. In ECCV .  Chen Sun Abhinav Shrivastava Carl Vondrick Kevin Murphy Rahul Sukthankar and Cordelia Schmid. 2018. Actor-centric relation network. In ECCV .","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Du Tran Lubomir Bourdev Rob Fergus Lorenzo Torresani and Manohar Paluri. 2015. Learning spatiotemporal features with 3d convolutional networks. In ICCV .  Du Tran Lubomir Bourdev Rob Fergus Lorenzo Torresani and Manohar Paluri. 2015. Learning spatiotemporal features with 3d convolutional networks. In ICCV .","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_42_1","volume-title":"Actor Conditioned Attention Maps for Video Action Detection. arXiv preprint arXiv:1812.11631","author":"Ulutan Oytun","year":"2018"},{"key":"e_1_3_2_1_43_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS .  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS ."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Heng Wang Alexander Kl\"aser Cordelia Schmid and Liu Cheng-Lin. 2011. Action recognition by dense trajectories. In CVPR .  Heng Wang Alexander Kl\"aser Cordelia Schmid and Liu Cheng-Lin. 2011. Action recognition by dense trajectories. In CVPR .","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Heng Wang and Cordelia Schmid. 2013. Action recognition with improved trajectories. In ICCV .  Heng Wang and Cordelia Schmid. 2013. Action recognition with improved trajectories. In ICCV .","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Shiyao Wang Yucong Zhou Junjie Yan and Zhidong Deng. 2018. Fully Motion-Aware Network for Video Object Detection. In ECCV .  Shiyao Wang Yucong Zhou Junjie Yan and Zhidong Deng. 2018. Fully Motion-Aware Network for Video Object Detection. In ECCV .","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Xiaolong Wang and Abhinav Gupta. 2018. Videos as space-time region graphs. In ECCV .  Xiaolong Wang and Abhinav Gupta. 2018. Videos as space-time region graphs. In ECCV .","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Philippe Weinzaepfel Zaid Harchaoui and Cordelia Schmid. 2015. Learning to track for spatio-temporal action localization. In ICCV .  Philippe Weinzaepfel Zaid Harchaoui and Cordelia Schmid. 2015. Learning to track for spatio-temporal action localization. In ICCV .","DOI":"10.1109\/ICCV.2015.362"},{"key":"e_1_3_2_1_49_1","unstructured":"Chao-Yuan Wu Christoph Feichtenhofer Haoqi Fan Kaiming He Philipp Krahenbuhl and Ross Girshick. 2019. Long-term feature banks for detailed video understanding. In CVPR .  Chao-Yuan Wu Christoph Feichtenhofer Haoqi Fan Kaiming He Philipp Krahenbuhl and Ross Girshick. 2019. Long-term feature banks for detailed video understanding. In CVPR ."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Fanyi Xiao and Yong Jae Lee. 2018. Video object detection with an aligned spatial-temporal memory. In ECCV .  Fanyi Xiao and Yong Jae Lee. 2018. Video object detection with an aligned spatial-temporal memory. In ECCV .","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Zhenheng Yang Jiyang Gao and Ram Nevatia. 2017. Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation. In BMVC .  Zhenheng Yang Jiyang Gao and Ram Nevatia. 2017. Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation. In BMVC .","DOI":"10.5244\/C.31.95"},{"key":"e_1_3_2_1_52_1","unstructured":"Bangpeng Yao and Li Fei-Fei. 2010. Modeling mutual context of object and human pose in human-object interaction activities. In CVPR .  Bangpeng Yao and Li Fei-Fei. 2010. Modeling mutual context of object and human pose in human-object interaction activities. In CVPR ."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2018. Exploring visual relationship for image captioning. In ECCV .  Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2018. Exploring visual relationship for image captioning. In ECCV .","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2019. Hierarchy Parsing for Image Captioning. In ICCV .  Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2019. Hierarchy Parsing for Image Captioning. In ICCV .","DOI":"10.1109\/ICCV.2019.00271"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Aditya Khosla Agata Lapedriza Aude Oliva and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR .  Bolei Zhou Aditya Khosla Agata Lapedriza Aude Oliva and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR .","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_56_1","unstructured":"Xizhou Zhu Jifeng Dai Lu Yuan and Yichen Wei. 2018. Towards high performance video object detection. In CVPR .  Xizhou Zhu Jifeng Dai Lu Yuan and Yichen Wei. 2018. Towards high performance video object detection. In CVPR ."},{"key":"e_1_3_2_1_57_1","unstructured":"Xizhou Zhu Yujie Wang Jifeng Dai Lu Yuan and Yichen Wei. 2017. Flow-guided feature aggregation for video object detection. In ICCV .  Xizhou Zhu Yujie Wang Jifeng Dai Lu Yuan and Yichen Wei. 2017. Flow-guided feature aggregation for video object detection. In ICCV ."}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350978","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":57,"alternative-id":["10.1145\/3343031.3350978","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350978","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}