{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:57:57Z","timestamp":1767085077140,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T00:00:00Z","timestamp":1576800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,12,20]]},"DOI":"10.1145\/3377170.3377253","type":"proceedings-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T11:16:22Z","timestamp":1584702982000},"page":"212-217","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["An Efficient Non-local Attention Network for Video-based Person Re-identification"],"prefix":"10.1145","author":[{"given":"Zhen","family":"Wang","sequence":"first","affiliation":[{"name":"Advanced Research Institute of Zhejiang Dahua Technology Co. Ltd, Hangzhou, China"}]},{"given":"Shixian","family":"Luo","sequence":"additional","affiliation":[{"name":"Advanced Research Institute of Zhejiang Dahua Technology Co. Ltd, Hangzhou, China"}]},{"given":"He","family":"Sun","sequence":"additional","affiliation":[{"name":"Advanced Research Institute of Zhejiang Dahua Technology Co. Ltd, Hangzhou, China"}]},{"given":"Huadong","family":"Pan","sequence":"additional","affiliation":[{"name":"Advanced Research Institute of Zhejiang Dahua Technology Co. Ltd, Hangzhou, China"}]},{"given":"Jun","family":"Yin","sequence":"additional","affiliation":[{"name":"Advanced Research Institute of Zhejiang Dahua Technology Co. Ltd, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2020,3,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00226"},{"key":"e_1_3_2_1_2_1","volume-title":"Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach[J]","author":"He L","year":"2018","unstructured":"He L , Liang J , Li H , Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach[J] . 2018 . DOI= http:\/\/dx.doi.org\/10.1109\/CVPR.2018.00739. 10.1109\/CVPR.2018.00739 He L, Liang J, Li H, et al. Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach[J]. 2018. DOI= http:\/\/dx.doi.org\/10.1109\/CVPR.2018.00739."},{"key":"e_1_3_2_1_3_1","volume-title":"IEEE, 2018","author":"Kalayeh M M","year":"2018","unstructured":"Kalayeh M M , Basaran E , Gokmen M , Human Semantic Parsing for Person Re-identification[C]\/\/ 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, 2018 . DOI= http:\/\/dx.doi.org\/10.1109\/CVPR. 2018 .00117. 10.1109\/CVPR.2018.00117 Kalayeh M M, Basaran E, Gokmen M, et al. Human Semantic Parsing for Person Re-identification[C]\/\/ 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018. DOI= http:\/\/dx.doi.org\/10.1109\/CVPR.2018.00117."},{"key":"e_1_3_2_1_4_1","volume-title":"Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)[C]\/\/","author":"Sun Y","year":"2017","unstructured":"Sun Y , Liang Z , Yi Y , Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)[C]\/\/ 2017 . DOI= http:\/\/dx.doi.org\/10.1007\/978-3-030-01225-0_30. 10.1007\/978-3-030-01225-0_30 Sun Y, Liang Z, Yi Y, et al. Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)[C]\/\/ 2017. DOI= http:\/\/dx.doi.org\/10.1007\/978-3-030-01225-0_30."},{"key":"e_1_3_2_1_5_1","volume-title":"IEEE, 2017","author":"Zhao H","year":"2017","unstructured":"Zhao H , Tian M , Sun S , Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion[C]\/\/ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, 2017 . DOI= http:\/\/dx.doi.org\/10.1109\/CVPR. 2017 .103. 10.1109\/CVPR.2017.103 Zhao H, Tian M, Sun S, et al. Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion[C]\/\/ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017. DOI= http:\/\/dx.doi.org\/10.1109\/CVPR.2017.103."},{"key":"e_1_3_2_1_6_1","unstructured":"Wei L Zhang S Yao H etal GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval[J]. DOI= http:\/\/dx.doi.org\/10.1145\/31233266.313279.    10.1145\/31233266.313279\nWei L Zhang S Yao H et al. GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval[J]. DOI= http:\/\/dx.doi.org\/10.1145\/31233266.313279."},{"key":"e_1_3_2_1_7_1","volume":"2017","author":"Liang Zheng","unstructured":"Liang Zheng , Yujia Huang, Huchuan Lu , et al. Pose Invariant Embedding for Deep Person Re-identification[J]. IEEE Transactions on Image Processing , 2017 , PP(99). DOI=http:\/\/dx.doi.org\/10.1109\/TIP.2019.2910414. 10.1109\/TIP.2019.2910414 Liang Zheng, Yujia Huang, Huchuan Lu, et al. Pose Invariant Embedding for Deep Person Re-identification[J]. IEEE Transactions on Image Processing, 2017, PP(99). DOI=http:\/\/dx.doi.org\/10.1109\/TIP.2019.2910414.","journal-title":"Pose Invariant Embedding for Deep Person Re-identification[J]. IEEE Transactions on Image Processing"},{"key":"e_1_3_2_1_8_1","volume-title":"MARS: A Video Benchmark for Large-Scale Person Re-Identification[C]\/\/ European Conference on Computer Vision","author":"Zheng L","year":"2016","unstructured":"Zheng L , Bie Z , Sun Y , MARS: A Video Benchmark for Large-Scale Person Re-Identification[C]\/\/ European Conference on Computer Vision . Springer International Publishing , 2016 . DOI=http:\/\/dx.doi.org\/10.1007\/978-3-319-46466-4_52. 10.1007\/978-3-319-46466-4_52 Zheng L, Bie Z, Sun Y, et al. MARS: A Video Benchmark for Large-Scale Person Re-Identification[C]\/\/ European Conference on Computer Vision. Springer International Publishing, 2016. DOI=http:\/\/dx.doi.org\/10.1007\/978-3-319-46466-4_52."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.150"},{"key":"e_1_3_2_1_10_1","volume-title":"IEEE, 2016","author":"Mclaughlin N","year":"2016","unstructured":"Mclaughlin N , Rincon J M D , Miller P. Recurrent Convolutional Network for Video-Based Person Re-identification[C]\/\/ 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, 2016 . DOI=http:\/\/dx.doi.org\/10.1109\/CVPR. 2016 .148. 10.1109\/CVPR.2016.148 Mclaughlin N, Rincon J M D, Miller P. Recurrent Convolutional Network for Video-Based Person Re-identification[C]\/\/ 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2016.148."},{"key":"e_1_3_2_1_11_1","volume-title":"Person Re-identification via Recurrent Feature Aggregation[C]\/\/ European Conference on Computer Vision","author":"Yan Y","year":"2016","unstructured":"Yan Y , Ni B , Song Z , Person Re-identification via Recurrent Feature Aggregation[C]\/\/ European Conference on Computer Vision . Springer International Publishing , 2016 . DOI=http:\/\/dx.doi.org\/10.1007\/978-3-319-46466-4_42. 10.1007\/978-3-319-46466-4_42 Yan Y, Ni B, Song Z, et al. Person Re-identification via Recurrent Feature Aggregation[C]\/\/ European Conference on Computer Vision. Springer International Publishing, 2016. DOI=http:\/\/dx.doi.org\/10.1007\/978-3-319-46466-4_42."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00243"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"e_1_3_2_1_14_1","volume-title":"Non-local Neural Networks[J]","author":"Wang X","year":"2017","unstructured":"Wang X , Girshick R , Gupta A , Non-local Neural Networks[J] . 2017 . Wang X, Girshick R, Gupta A, et al. Non-local Neural Networks[J]. 2017."},{"key":"e_1_3_2_1_15_1","volume-title":"Revisiting Temporal Modeling for Video-based Person ReID[J]","author":"Gao J","year":"2018","unstructured":"Gao J , Nevatia R. Revisiting Temporal Modeling for Video-based Person ReID[J] . 2018 . Gao J, Nevatia R. Revisiting Temporal Modeling for Video-based Person ReID[J]. 2018."},{"key":"e_1_3_2_1_16_1","volume-title":"Sta: Spatial-temporal attention for large-scale video-based person re-identification[C]","author":"Yang F","year":"2019","unstructured":"Yang F , Xiaoyang W , Yunchao W , Sta: Spatial-temporal attention for large-scale video-based person re-identification[C] . 2019 . Yang F, Xiaoyang W, Yunchao W, et al. Sta: Spatial-temporal attention for large-scale video-based person re-identification[C]. 2019."},{"key":"e_1_3_2_1_17_1","volume-title":"VRSTC: Occlusion-Free Video Person Re-Identification[J]","author":"Hou R","year":"2019","unstructured":"Hou R , Ma B , Chang H , VRSTC: Occlusion-Free Video Person Re-Identification[J] . 2019 . Hou R, Ma B, Chang H, et al. VRSTC: Occlusion-Free Video Person Re-Identification[J]. 2019."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Yiru Zhao Xu Shen Zhongming Jin et al. Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification.2019.  Yiru Zhao Xu Shen Zhongming Jin et al. Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification.2019.","DOI":"10.1109\/CVPR.2019.00505"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00046"},{"key":"e_1_3_2_1_20_1","volume-title":"Wang Y C F, et al. Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification[J]","author":"Liu C T","year":"2019","unstructured":"Liu C T , Wu C W , Wang Y C F, et al. Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification[J] . 2019 . Liu C T, Wu C W, Wang Y C F, et al. Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification[J]. 2019."},{"key":"e_1_3_2_1_21_1","volume-title":"Dual Attention Network for Scene Segmentation[J]","author":"Fu J","year":"2018","unstructured":"Fu J , Liu J , Tian H , Dual Attention Network for Scene Segmentation[J] . 2018 . Fu J, Liu J, Tian H, et al. Dual Attention Network for Scene Segmentation[J]. 2018."},{"key":"e_1_3_2_1_22_1","volume-title":"CCNet: Criss-Cross Attention for Semantic Segmentation[J]","author":"Huang Z","year":"2018","unstructured":"Huang Z , Wang X , Huang L , CCNet: Criss-Cross Attention for Semantic Segmentation[J] . 2018 . Huang Z, Wang X, Huang L, et al. CCNet: Criss-Cross Attention for Semantic Segmentation[J]. 2018."},{"key":"e_1_3_2_1_23_1","volume-title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond. arXiv:1904","author":"Yue C","year":"2019","unstructured":"Yue C , Jiarui X , Stephen L , GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond. arXiv:1904 .11492, 2019 . Yue C, Jiarui X, Stephen L, et al. GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond. arXiv:1904.11492, 2019."},{"key":"e_1_3_2_1_24_1","volume-title":"Deep Residual Learning for Image Recognition[J]","author":"He K","year":"2015","unstructured":"He K , Zhang X , Ren S , Deep Residual Learning for Image Recognition[J] . 2015 . DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2016.90. 10.1109\/CVPR.2016.90 He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[J]. 2015. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2016.90."},{"key":"e_1_3_2_1_25_1","unstructured":"Hermans A Beyer L Leibe B. In Defense of the Triplet Loss for Person Re-Identification[J]. 2017  Hermans A Beyer L Leibe B. In Defense of the Triplet Loss for Person Re-Identification[J]. 2017"},{"key":"e_1_3_2_1_26_1","volume-title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition[J]","author":"Wang H","year":"2018","unstructured":"Wang H , Wang Y , Zhou Z , CosFace: Large Margin Cosine Loss for Deep Face Recognition[J] . 2018 . DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2018.00552. 10.1109\/CVPR.2018.00552 Wang H, Wang Y, Zhou Z, et al. CosFace: Large Margin Cosine Loss for Deep Face Recognition[J]. 2018. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2018.00552."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"e_1_3_2_1_28_1","volume-title":"IEEE, 2018","author":"Wu Y","year":"2018","unstructured":"Wu Y , Lin Y , Dong X , Exploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning[C]\/\/ 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, 2018 . DOI=http:\/\/dx.doi.org\/10.1109\/CVPR. 2018 .00543. 10.1109\/CVPR.2018.00543 Wu Y, Lin Y, Dong X, et al. Exploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning[C]\/\/ 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2018.00543."},{"key":"e_1_3_2_1_29_1","volume-title":"IEEE, 2015","author":"Zheng L","year":"2015","unstructured":"Zheng L , Shen L , Tian L , Scalable Person Re-identification: A Benchmark[C]\/\/ 2015 IEEE International Conference on Computer Vision (ICCV) . IEEE, 2015 . DOI=http:\/\/dx.doi.org\/10.1109\/ICCV. 2015 .133. 10.1109\/ICCV.2015.133 Zheng L, Shen L, Tian L, et al. Scalable Person Re-identification: A Benchmark[C]\/\/ 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015. DOI=http:\/\/dx.doi.org\/10.1109\/ICCV.2015.133."},{"key":"e_1_3_2_1_30_1","volume-title":"IEEE, 2005","author":"Bolle R M","year":"2005","unstructured":"Bolle R M , Connell J H , Pankanti S , The relation between the ROC curve and the CMC[C]\/\/ Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05) . IEEE, 2005 . DOI=http:\/\/dx.doi.org\/10.1109\/AUTOID. 2005 .48. 10.1109\/AUTOID.2005.48 Bolle R M, Connell J H, Pankanti S, et al. The relation between the ROC curve and the CMC[C]\/\/ Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05). IEEE, 2005. DOI=http:\/\/dx.doi.org\/10.1109\/AUTOID.2005.48."},{"key":"e_1_3_2_1_31_1","volume-title":"ImageNet: a Large-Scale Hierarchical Image Database[C]\/\/ 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR","author":"Deng J","year":"2009","unstructured":"Deng J , Dong W , Socher R , ImageNet: a Large-Scale Hierarchical Image Database[C]\/\/ 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009 ), 20-25 June 2009, Miami, Florida, USA. IEEE , 2009. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2009.5206848. 10.1109\/CVPR.2009.5206848 Deng J, Dong W, Socher R, et al. ImageNet: a Large-Scale Hierarchical Image Database[C]\/\/ 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20-25 June 2009, Miami, Florida, USA. IEEE, 2009. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2009.5206848."},{"key":"e_1_3_2_1_32_1","volume-title":"Computer Science","author":"Kingma D P","year":"2014","unstructured":"Kingma D P , Ba J. Adam : A Method for Stochastic Optimization[J] . Computer Science , 2014 . Kingma D P, Ba J. Adam: A Method for Stochastic Optimization[J]. Computer Science, 2014."},{"key":"e_1_3_2_1_33_1","volume-title":"IEEE, 2017","author":"Zhou Z","year":"2017","unstructured":"Zhou Z , Huang Y , Wang W , See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification[C]\/\/ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, 2017 . DOI=http:\/\/dx.doi.org\/10.1109\/CVPR. 2017 .717. 10.1109\/CVPR.2017.717 Zhou Z, Huang Y, Wang W, et al. See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification[C]\/\/ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017. DOI=http:\/\/dx.doi.org\/10.1109\/CVPR.2017.717."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.782"},{"key":"e_1_3_2_1_35_1","first-page":"1169","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Dapeng C","year":"2018","unstructured":"Dapeng C , Hongsheng L , Tong X , el al. Video person re-identification with competitive snippet-similarity aggregation and co-attentive . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages 1169 -- 1178 , 2018 . Dapeng C, Hongsheng L, Tong X, el al. Video person re-identification with competitive snippet-similarity aggregation and co-attentive. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1169--1178, 2018."}],"event":{"name":"ICIT 2019: IoT and Smart City","sponsor":["Shanghai Jiao Tong University Shanghai Jiao Tong University","The Hong Kong Polytechnic The Hong Kong Polytechnic University","University of Malaya University of Malaya"],"location":"Shanghai China","acronym":"ICIT 2019"},"container-title":["Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377170.3377253","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3377170.3377253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:41Z","timestamp":1750202621000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377170.3377253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,20]]},"references-count":35,"alternative-id":["10.1145\/3377170.3377253","10.1145\/3377170"],"URL":"https:\/\/doi.org\/10.1145\/3377170.3377253","relation":{},"subject":[],"published":{"date-parts":[[2019,12,20]]},"assertion":[{"value":"2020-03-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}