{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:27:46Z","timestamp":1760956066094,"version":"3.40.3"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585884"},{"type":"electronic","value":"9783030585891"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58589-1_43","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T06:18:04Z","timestamp":1605075484000},"page":"718-736","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":73,"title":["Detecting Human-Object Interactions with Action Co-occurrence Priors"],"prefix":"10.1007","author":[{"given":"Dong-Jin","family":"Kim","sequence":"first","affiliation":[]},{"given":"Xiao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jinsoo","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Stephen","family":"Lin","sequence":"additional","affiliation":[]},{"given":"In So","family":"Kweon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Bansal, A., Rambhatla, S.S., Shrivastava, A., Chellappa, R.: Detecting human-object interactions via functional generalization. In: AAAI Conference on Artificial Intelligence (AAAI) (2020)","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"43_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-030-01261-8_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"F Baradel","year":"2018","unstructured":"Baradel, F., Neverova, N., Wolf, C., Mille, J., Mori, G.: Object level visual reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 106\u2013122. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_7"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Wang, Z., He, Y., Wang, J., Deng, J.: HICO: a benchmark for recognizing human-object interactions in images. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.122"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"43_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/978-3-642-33783-3_21","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V Delaitre","year":"2012","unstructured":"Delaitre, V., Fouhey, D.F., Laptev, I., Sivic, J., Gupta, A., Efros, A.A.: Scene semantics from long-term observation of people. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 284\u2013298. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_21"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Delaitre, V., Laptev, I., Sivic, J.: Recognizing human actions in still images: a study of bag-of-features and part-based representations. In: British Machine Vision Conference (BMVC) (2010)","DOI":"10.5244\/C.24.97"},{"key":"43_CR8","unstructured":"Delaitre, V., Sivic, J., Laptev, I.: Learning person-object interactions for action recognition in still images. In: Advances in Neural Information Processing Systems (NIPS) (2011)"},{"key":"43_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-319-10590-1_4","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Deng","year":"2014","unstructured":"Deng, J., et al.: Large-scale object classification using label relation graphs. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 48\u201364. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_4"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"43_CR11","unstructured":"Gao, C., Zou, Y., Huang, J.B.: iCAN: instance-centric attention network for human-object interaction detection. In: British Machine Vision Conference (BMVC) (2018)"},{"key":"43_CR12","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218","volume-title":"The Ecological Approach to Visual Perception","author":"JJ Gibson","year":"2014","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception, Classic edn. Psychology Press, New York (2014)","edition":"Classic"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.S.: Objects in action: an approach for combining action understanding and object perception. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2007)","DOI":"10.1109\/CVPR.2007.383331"},{"key":"43_CR16","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"43_CR17","unstructured":"Gupta, T., Schwing, A., Hoiem, D.: No-Frills Pytorch Github. https:\/\/github.com\/BigRedT\/no_frills_hoi_det"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, T., Schwing, A., Hoiem, D.: No-frills human-object interaction detection: factorization, layout encodings, and training techniques. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00977"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR20","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"43_CR21","first-page":"1279","volume":"42","author":"S Horiguchi","year":"2019","unstructured":"Horiguchi, S., Ikami, D., Aizawa, K.: Significance of softmax-based features in comparison to distance metric learning-based features. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 42, 1279\u20131285 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Hu, Z., Ma, X., Liu, Z., Hovy, E., Xing, E.: Harnessing deep neural networks with logic rules. In: Annual Meeting of the Association for Computational Linguistics (ACL) (2016)","DOI":"10.18653\/v1\/P16-1228"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Hwang, S.J., Sha, F., Grauman, K.: Sharing features between objects and their attributes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)","DOI":"10.1109\/CVPR.2011.5995543"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"43_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-01264-9_15","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Kato","year":"2018","unstructured":"Kato, K., Li, Y., Gupta, A.: Compositional learning for human object interaction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 247\u2013264. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_15"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Kim, D.J., Choi, J., Oh, T.H., Kweon, I.S.: Dense relational captioning: triple-stream networks for relationship-based captioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00643"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Kim, D.J., Choi, J., Oh, T.H., Kweon, I.S.: Image captioning with very scarce supervised data: adversarial semi-supervised learning approach. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)","DOI":"10.18653\/v1\/D19-1208"},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Kim, D.J., Choi, J., Oh, T.H., Yoon, Y., Kweon, I.S.: Disjoint multi-task learning between heterogeneous human-centric tasks. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00189"},{"key":"43_CR29","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)"},{"issue":"1","key":"43_CR30","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"43_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Wang, X.: VIP-CNN: a visual phrase reasoning convolutional neural network for visual relationship detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.766"},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Detailed 2D\u20133D joint representation for human-object interaction. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"43_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Transferable interactiveness knowledge for human-object interaction detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00370"},{"key":"43_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-319-46493-0_37","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Li","year":"2016","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 614\u2013629. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_37"},{"key":"43_CR35","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Feng, J.: PPDM: parallel point detection and matching for real-time human-object interaction detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"43_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"43_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"43_CR38","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Schmid, C.: Semantic hierarchies for visual object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2007)","DOI":"10.1109\/CVPR.2007.383272"},{"issue":"11","key":"43_CR39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"43_CR40","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"43_CR41","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Detecting unseen visual relations using analogies. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00207"},{"key":"43_CR42","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Mallya, A., Cervantes, C.M., Hockenmaier, J., Lazebnik, S.: Phrase localization and visual relationship detection with comprehensive linguistic cues (2017)","DOI":"10.1109\/ICCV.2017.213"},{"key":"43_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-030-01240-3_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Qi","year":"2018","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.-C.: Learning human-object interactions by graph parsing neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 407\u2013423. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_25"},{"key":"43_CR44","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)"},{"key":"43_CR45","doi-asserted-by":"crossref","unstructured":"Shen, L., Yeung, S., Hoffman, J., Mori, G., Fei-Fei, L.: Scaling human-object interaction recognition through zero-shot learning. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00181"},{"issue":"10","key":"43_CR46","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/34.99242","volume":"13","author":"L Stark","year":"1991","unstructured":"Stark, L., Bowyer, K.: Achieving generalized object recognition through reasoning about association of function to structure. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 13(10), 1097\u20131104 (1991)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"43_CR47","doi-asserted-by":"crossref","unstructured":"Sun, X., Li, C., Lin, S.: Explicit spatiotemporal joint relation learning for tracking human pose. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00344"},{"key":"43_CR48","doi-asserted-by":"crossref","unstructured":"Sun, X., Wei, Y., Liang, S., Tang, X., Sun, J.: Cascaded hand pose regression. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298683"},{"key":"43_CR49","doi-asserted-by":"crossref","unstructured":"Ulutan, O., Iftekhar, A., Manjunath, B.: VSGNet: spatial attention network for detecting human object interactions using graph convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"43_CR50","doi-asserted-by":"crossref","unstructured":"Wan, B., Zhou, D., Liu, Y., Li, R., He, X.: Pose-aware multi-level feature network for human object interaction detection. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00956"},{"key":"43_CR51","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Deep contextual attention for human-object interaction detection. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00579"},{"key":"43_CR52","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: Learning human-object interaction detection using interaction points. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"43_CR53","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1109\/TMM.2019.2943753","volume":"22","author":"B Xu","year":"2019","unstructured":"Xu, B., Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Interact as you intend: intention-driven human-object interaction detection. IEEE Trans. Multimed. 22, 1423\u20131432 (2019)","journal-title":"IEEE Trans. Multimed."},{"key":"43_CR54","doi-asserted-by":"crossref","unstructured":"Xu, B., Wong, Y., Li, J., Zhao, Q., Kankanhalli, M.S.: Learning to detect human-object interactions with knowledge. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00212"},{"key":"43_CR55","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"43_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01258-8_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Yang","year":"2018","unstructured":"Yang, X., Zhang, H., Cai, J.: Shuffle-then-assemble: learning object-agnostic visual relationship features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 38\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_3"},{"key":"43_CR57","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: GroupLet: a structured image representation for recognizing human and object interactions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"43_CR58","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"43_CR59","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: IEEE International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"43_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-030-01219-9_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Yin","year":"2018","unstructured":"Yin, G., et al.: Zoom-Net: mining deep feature interactions for visual relationship recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 330\u2013347. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_20"},{"key":"43_CR61","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Visual relationship detection with internal and external linguistic knowledge distillation. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"43_CR62","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Yu, J., Yu, T., Tao, D.: On exploring undetermined relationships for visual relationship detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00527"},{"key":"43_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, H., Wang, C., Xie, J.: Co-occurrent features in semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00064"},{"key":"43_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"43_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, J., Elhoseiny, M., Cohen, S., Chang, W., Elgammal, A.: Relationship proposal networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.555"},{"key":"43_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, P., Chi, M.: Relation parsing neural network for human-object interaction detection. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00093"},{"key":"43_CR67","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Liu, L., Shen, C., Reid, I.: Towards context-aware interaction recognition for visual relationship detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/ICCV.2017.71"},{"key":"43_CR68","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., van den Hengel, A.: HCVRD: a benchmark for large-scale human-centered visual relationship detection. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.12260"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58589-1_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:26:04Z","timestamp":1731284764000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58589-1_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585884","9783030585891"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58589-1_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}