{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:01:00Z","timestamp":1773414060030,"version":"3.50.1"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198113","type":"print"},{"value":"9783031198120","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19812-0_11","type":"book-chapter","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T14:03:42Z","timestamp":1667052222000},"page":"178-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":103,"title":["Panoptic Scene Graph Generation"],"prefix":"10.1007","author":[{"given":"Jingkang","family":"Yang","sequence":"first","affiliation":[]},{"given":"Yi Zhe","family":"Ang","sequence":"additional","affiliation":[]},{"given":"Zujin","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Kaiyang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Wayne","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,30]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.cviu.2017.12.004","volume":"173","author":"S Aditya","year":"2018","unstructured":"Aditya, S., Yang, Y., Baral, C., Aloimonos, Y., Ferm\u00fcller, C.: Image understanding using vision and reasoning through scene description graph. Comput. Vis. Image Understand. 173, 33\u201345 (2018)","journal-title":"Comput. Vis. Image Understand."},{"key":"11_CR2","doi-asserted-by":"publisher","first-page":"5560","DOI":"10.1109\/LRA.2022.3157567","volume":"7","author":"S Amiri","year":"2022","unstructured":"Amiri, S., Chandan, K., Zhang, S.: Reasoning with scene graphs for robot planning under partial observability. IEEE Robot. Autom. Lett. 7, 5560\u20135567 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 (2016)","DOI":"10.1162\/tacl_a_00051"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv preprint arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"11_CR5","unstructured":"Chang, X., Ren, P., Xu, P., Li, Z., Chen, X., Hauptmann, A.: Scene graphs: a survey of generations and applications. arXiv preprint arXiv:2104.01111 (2021)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"11_CR7","unstructured":"Chen, K., et al.: Mmdetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Wang, P., Wu, Q.: Say as you wish: fine-grained control of image caption generation with abstract scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., Lin, L.: Knowledge-embedded routing network for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00632"},{"key":"11_CR10","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. vol. abs\/2107.06278 (2021)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Desai, A., Wu, T.Y., Tripathi, S., Vasconcelos, N.: Learning of visual relations: the devil is in the tails. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Dhamo, H., et al.: Semantic image manipulation using scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Gadre, S.Y., Ehsani, K., Song, S., Mottaghi, R.: Continuous scene representations for embodied AI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01443"},{"key":"11_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-030-58610-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gao","year":"2020","unstructured":"Gao, C., Xu, J., Zou, Y., Huang, J.-B.: DRG: dual relation graph for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 696\u2013712. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_41"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Gao, L., Wang, B., Wang, W.: Image captioning with scene-graph based semantic concepts. In: Proceedings of the International Conference on Machine Learning and Computing (2018)","DOI":"10.1145\/3195106.3195114"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., Ling, M.: Scene graph generation with external knowledge and image reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00207"},{"key":"11_CR19","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR21","unstructured":"Hildebrandt, M., Li, H., Koner, R., Tresp, V., G\u00fcnnemann, S.: Scene graph reasoning for visual question answering. In: ICML Workshop Graph Representation Learning and Beyond (GRL+) (2020)"},{"key":"11_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-030-58555-6_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Hou","year":"2020","unstructured":"Hou, Z., Peng, X., Qiao, Yu., Tao, D.: Visual compositional learning for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 584\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_35"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yu, B., Qiao, Y., Peng, X., Tao, D.: Affordance transfer learning for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: Gqa: A new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"11_CR25","doi-asserted-by":"publisher","first-page":"3820","DOI":"10.1109\/TPAMI.2020.2992222","volume":"43","author":"ZS Hung","year":"2020","unstructured":"Hung, Z.S., Mallya, A., Lazebnik, S.: Contextual translation embedding for visual relationship detection and scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 43, 3820\u20133832 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"11_CR28","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":"11_CR29","doi-asserted-by":"crossref","unstructured":"Khandelwal, S., Suhail, M., Sigal, L.: Segmentation-grounded scene graph generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01558"},{"key":"11_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-030-58555-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Kim","year":"2020","unstructured":"Kim, B., Choi, T., Kang, J., Kim, H.J.: UnionDet: union-level detector towards real-time human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 498\u2013514. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_30"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: Hotr: end-to-end human-object interaction detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Kuznetsova, A., Lampert, C., Ferrari, V.: Detecting visual relationships using box attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (CVPR-W) (2019)","DOI":"10.1109\/ICCVW.2019.00217"},{"key":"11_CR35","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, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"11_CR36","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logist. Quart. 2, 83\u201397 (1955)","journal-title":"Naval Res. Logist. Quart."},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., Xiao, J.: The devil is in the labels: noisy label correction for robust scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"11_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-01246-5_21","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Ouyang, W., Zhou, B., Shi, J., Zhang, C., Wang, X.: Factorizable net: an efficient subgraph-based framework for scene graph generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 346\u2013363. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_21"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Detailed 2D\u20133D joint representation for human-object interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Transferable interactiveness knowledge for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00370"},{"key":"11_CR41","unstructured":"Li, Z., et al.: Panoptic segformer. arXiv preprint arXiv:2109.03814 (2021)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Liang, Y., Bai, Y., Zhang, W., Qian, X., Zhu, L., Mei, T.: VRR-VG: refocusing visually-relevant relationships. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01050"},{"key":"11_CR43","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":"T-Y 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":"11_CR44","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., Tao, D.: GPS-Net: graph property sensing network for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"11_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58568-6_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Chen, Q., Zisserman, A.: Amplifying key cues for human-object-interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 248\u2013265. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_15"},{"key":"11_CR46","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":"11_CR47","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: International Conference on 3D Vision (3DV) (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Peyre, J., Sivic, J., Laptev, I., Schmid, C.: Weakly-supervised learning of visual relations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.554"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Qi, M., Li, W., Yang, Z., Wang, Y., Luo, J.: Attentive relational networks for mapping images to scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00408"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Qi, M., Wang, Y., Li, A.: Online cross-modal scene retrieval by binary representation and semantic graph. In: Proceedings of the ACM International Conference on Multimedia (ACM MM) (2017)","DOI":"10.1145\/3123266.3123311"},{"key":"11_CR51","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 (2015)"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Schuster, S., Krishna, R., Chang, A., Fei-Fei, L., Manning, C.D.: Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In: Proceedings of the Fourth Workshop on Vision and language (2015)","DOI":"10.18653\/v1\/W15-2812"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Shi, J., Zhang, H., Li, J.: Explainable and explicit visual reasoning over scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00857"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Suhail, M., et al.: Energy-based learning for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H., Yoshinaga, T.: Qpic: query-based pairwise human-object interaction detection with image-wide contextual information. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"11_CR56","unstructured":"Tang, K.: A scene graph generation codebase in pytorch (2020). https:\/\/github.com\/KaihuaTang\/Scene-Graph-Benchmark.pytorch"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"11_CR58","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Wang, S., Duan, Y., Ding, H., Tan, Y.P., Yap, K.H., Yuan, J.: Learning transferable human-object interaction detector with natural language supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"11_CR60","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Deep contextual attention for human-object interaction detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00579"},{"key":"11_CR61","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"11_CR62","unstructured":"Wang, W.: Mmscenegraph (2021). https:\/\/github.com\/Kenneth-Wong\/MMSceneGraph"},{"key":"11_CR63","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Upsnet: A unified panoptic segmentation network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"11_CR64","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"11_CR65","unstructured":"Xu, P., Chang, X., Guo, L., Huang, P.Y., Chen, X., Hauptmann, A.G.: A survey of scene graph: Generation and application. IEEE Trans. Neural Networks Learn. Syst. (TNNLS) (2020)"},{"key":"11_CR66","doi-asserted-by":"crossref","unstructured":"Yang, C.A., Tan, C.Y., Fan, W.C., Yang, C.F., Wu, M.L., Wang, Y.C.F.: Scene graph expansion for semantics-guided image outpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01517"},{"key":"11_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01246-5_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Yang","year":"2018","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Graph R-CNN for scene graph\u00a0generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_41"},{"key":"11_CR68","doi-asserted-by":"crossref","unstructured":"Ye, K., Kovashka, A.: Linguistic structures as weak supervision for visual scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00819"},{"key":"11_CR69","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-030-58592-1_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zareian","year":"2020","unstructured":"Zareian, A., Karaman, S., Chang, S.-F.: Bridging knowledge graphs to generate scene graphs. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 606\u2013623. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_36"},{"key":"11_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/978-3-030-58592-1_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zareian","year":"2020","unstructured":"Zareian, A., Wang, Z., You, H., Chang, S.-F.: Learning visual commonsense for robust scene graph generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 642\u2013657. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_38"},{"key":"11_CR71","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: Scene graph parsing with global context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"11_CR72","unstructured":"Zhang, A., et al.: Mining the benefits of two-stage and one-stage hoi detection. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"11_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"11_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"11_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, J., Elhoseiny, M., Cohen, S., Chang, W., Elgammal, A.: Relationship proposal networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.555"},{"key":"11_CR76","unstructured":"Zhang, W., Pang, J., Chen, K., Loy, C.C.: K-Net: towards unified image segmentation. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"11_CR77","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Shi, J., Yang, J., Xu, C., Li, Y.: Learning to generate scene graph from natural language supervision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00184"},{"key":"11_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Qi, S., Ling, H., Shen, J.: Cascaded human-object interaction recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"11_CR79","doi-asserted-by":"crossref","unstructured":"Zou, C., et al.: End-to-end human object interaction detection with hoi transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19812-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T13:05:18Z","timestamp":1682600718000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19812-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198113","9783031198120"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19812-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"30 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}