{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T13:00:04Z","timestamp":1777640404187,"version":"3.51.4"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702193"],"award-info":[{"award-number":["61702193"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Program of Guangzhou","award":["201804010272"],"award-info":[{"award-number":["201804010272"]}]},{"name":"the Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2017ZT07X183"],"award-info":[{"award-number":["2017ZT07X183"]}]},{"name":"the Fundamental Research Funds for the Central Universities of China","award":["2019JQ01"],"award-info":[{"award-number":["2019JQ01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11263-021-01458-8","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T04:02:54Z","timestamp":1618804974000},"page":"1910-1929","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Polysemy Deciphering Network for Robust Human\u2013Object Interaction Detection"],"prefix":"10.1007","volume":"129","author":[{"given":"Xubin","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7232-3181","authenticated-orcid":false,"given":"Changxing","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"1458_CR1","doi-asserted-by":"crossref","unstructured":"Bansal, A., Rambhatla, S., Shrivastava, A., & Chellappa, R. (2020). Detecting human\u2013object interactions via functional generalization. In AAAI (pp. 10460\u201310469).","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"1458_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y., Liu, Y., Liu, X., Zeng, H., & Deng, J. (2018). Learning to detect human\u2013object interactions. In WACV (pp. 381\u2013389).","DOI":"10.1109\/WACV.2018.00048"},{"key":"1458_CR3","doi-asserted-by":"crossref","unstructured":"Chao, Y., Wang, Z., He, Y., Wang, J., & Deng, J. (2015). Hico: A benchmark for recognizing human\u2013object interactions in images. In ICCV (pp. 1017\u20131025).","DOI":"10.1109\/ICCV.2015.122"},{"key":"1458_CR4","unstructured":"Chen, X., & Gupta, A. (2017). An implementation of faster rcnn with study for region sampling. arXiv:1702.02138."},{"key":"1458_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., & Chua, T. (2017). Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In CVPR (pp. 5659\u20135667).","DOI":"10.1109\/CVPR.2017.667"},{"key":"1458_CR6","doi-asserted-by":"crossref","unstructured":"Damen, D., Doughty, H., Maria Farinella, G., Fidler, S., Furnari, A., Kazakos, E., Moltisanti, D., Munro, J., Perrett, T., & Price, W. (2018). Scaling egocentric vision: The epic-kitchens dataset. In ECCV (pp. 720\u2013736).","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"1458_CR7","doi-asserted-by":"crossref","unstructured":"Ding, C., Wang, K., Wang, P., & Tao, D. (2020). Multi-task learning with coarse priors for robust part-aware person re-identification. TPAMI.","DOI":"10.1109\/TPAMI.2020.3024900"},{"key":"1458_CR8","doi-asserted-by":"crossref","unstructured":"Fang, H., Xie, S., Tai, Y., & Lu, C. (2017). Rmpe: Regional multi-person pose estimation. In ICCV (pp. 382\u2013391).","DOI":"10.1109\/ICCV.2017.256"},{"key":"1458_CR9","doi-asserted-by":"crossref","unstructured":"Gao, P., Jiang, Z., You, H., Lu, P., Hoi, S., Wang, X., & Li, H. (2019). Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In CVPR (pp. 6639\u20136648).","DOI":"10.1109\/CVPR.2019.00680"},{"key":"1458_CR10","unstructured":"Gao, H., Zou, Y., & Huang, J. (2018). iCAN: Instance-Centric Attention Network for Human\u2013Object Interaction Detection. In BMVC (p. 41)."},{"key":"1458_CR11","unstructured":"Girdhar, R., & Ramanan, D. (2017). Attentional pooling for action recognition. In NeurIPS (pp. 34\u201345)."},{"key":"1458_CR12","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., & He, K. (2018). Detectron. https:\/\/github.com\/facebookresearch\/detectron."},{"key":"1458_CR13","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., & He, K. (2018). Detecting and recognizing human\u2013object interactions. In CVPR (pp. 8359\u20138367).","DOI":"10.1109\/CVPR.2018.00872"},{"key":"1458_CR14","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., & Ling, M. (2019). Scene graph generation with external knowledge and image reconstruction. In CVPR (pp. 1969\u20131978).","DOI":"10.1109\/CVPR.2019.00207"},{"key":"1458_CR15","unstructured":"Gupta, S., & Malik, J. (2015). Visual semantic role labeling. arXiv:1505.04474."},{"key":"1458_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, T., Schwing, A., & Hoiem, D. (2019). No-frills human\u2013object interaction detection: Factorization, layout encodings, and training techniques. In ICCV (pp. 9677\u20139685).","DOI":"10.1109\/ICCV.2019.00977"},{"key":"1458_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In ICCV (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"1458_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1458_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In CVPR (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1458_CR20","doi-asserted-by":"crossref","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., & Guadarrama, S., et\u00a0al. (2017). Speed\/accuracy trade-offs for modern convolutional object detectors. In CVPR (pp. 7310\u20137311).","DOI":"10.1109\/CVPR.2017.351"},{"key":"1458_CR21","unstructured":"Huang, E., Socher, R., Manning, C., & Ng, A. (2012). Improving word representations via global context and multiple word prototypes. In Proceedings of the 50th annual meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 873\u2013882)."},{"key":"1458_CR22","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et\u00a0al. (2015). Spatial transformer networks. In NeurIPS (pp. 2017\u20132025)."},{"key":"1458_CR23","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., & Niebles, J.C. (2020). Action genome: Actions as compositions of spatio-temporal scene graphs. In CVPR (pp. 10236\u201310247).","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"1458_CR24","doi-asserted-by":"crossref","unstructured":"Kato, K., Li, Y., & Gupta, A. (2018). Compositional learning for human object interaction. In ECCV (pp. 234\u2013251).","DOI":"10.1007\/978-3-030-01264-9_15"},{"key":"1458_CR25","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980."},{"issue":"1","key":"1458_CR26","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., et al. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. IJCV, 123(1), 32\u201373.","journal-title":"IJCV"},{"issue":"7","key":"1458_CR27","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., & Ferrari, V. (2020). The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. IJCV, 128(7), 1956\u20131981.","journal-title":"IJCV"},{"key":"1458_CR28","doi-asserted-by":"crossref","unstructured":"Li, B., Liang, J., & Wang, Y. (2019a). Compression artifact removal with stacked multi-context channel-wise attention network. In ICIP (pp. 3601\u20133605).","DOI":"10.1109\/ICIP.2019.8803448"},{"key":"1458_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, X., Lu, H., Wang, S., Liu, J., Li, J., & Lu, C. (2020a). Detailed 2d-3d joint representation for human\u2013object interaction. In CVPR (pp. 10166\u201310175).","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"1458_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Xu, L., Liu, X., Huang, X., Xu, Y., Wang, S., Fang, HS., Ma, Z., Chen, M., & Lu, C. (2020b). Pastanet: Toward human activity knowledge engine. In CVPR (pp. 382\u2013391).","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"1458_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhou, S., Huang, X., Xu, L., Ma, Z., Fang, HS., Wang, Y., & Lu, C. (2019b). Transferable interactiveness knowledge for human\u2013object interaction detection. In CVPR (pp. 3585\u20133594).","DOI":"10.1109\/CVPR.2019.00370"},{"key":"1458_CR32","doi-asserted-by":"crossref","unstructured":"Li, W., Zhu, X., & Gong, S. (2018). Harmonious attention network for person re-identification. In CVPR (pp. 2285\u20132294).","DOI":"10.1109\/CVPR.2018.00243"},{"key":"1458_CR33","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., & Feng, J. (2020). Ppdm: Parallel point detection and matching for real-time human\u2013object interaction detection. In CVPR (pp. 482\u2013490).","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"1458_CR34","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., & Tao, D. (2020). Gps-net: Graph property sensing network for scene graph generation. In CVPR (pp. 3746\u20133753).","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"1458_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In CVPR (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1458_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In ECCV (pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1458_CR37","doi-asserted-by":"crossref","unstructured":"Liu, N., Tan, Q., Li, Y., Yang, H., Zhou, J., & Hu, X. (2019). Is a single vector enough? exploring node polysemy for network embedding. In ACM SIGKDD (pp. 932\u2013940).","DOI":"10.1145\/3292500.3330967"},{"key":"1458_CR38","unstructured":"Lu, J., Batra, D., Parikh, D., & Lee, S. (2019). Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In NeurIPS (pp. 13\u201323)."},{"key":"1458_CR39","doi-asserted-by":"crossref","unstructured":"Lu, C., Krishna, R., Bernstein, M., & Fei-Fei, L. (2016). Visual relationship detection with language priors. In ECCV (pp. 852\u2013869).","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"1458_CR40","doi-asserted-by":"crossref","unstructured":"Ma, R., Jin, L., Liu, Q., Chen, L., & Yu, K. (2020). Addressing the polysemy problem in language modeling with attentional multi-sense embeddings. In ICASSP (pp. 8129\u20138133).","DOI":"10.1109\/ICASSP40776.2020.9053503"},{"key":"1458_CR41","unstructured":"MacQueen, J., et\u00a0al. (1967). Some methods for classification and analysis of multivariate observations. In the Processing of the fifth Berkeley symposium on mathematical statistics and probability (pp. 281\u2013297)."},{"key":"1458_CR42","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., & Mottaghi, R. (2019). Ok-vqa: A visual question answering benchmark requiring external knowledge. In CVPR (pp. 3195\u20133204).","DOI":"10.1109\/CVPR.2019.00331"},{"key":"1458_CR43","unstructured":"Massa, F., & Girshick, R. (2018). maskrcnn-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch. https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark."},{"key":"1458_CR44","doi-asserted-by":"crossref","unstructured":"Meng, L., Zhao, B., Chang, B., Huang, G., Sun, W., Tung, F., & Sigal, L. (2019). Interpretable spatio-temporal attention for video action recognition. In ICCV workshops (pp. 1513\u20131522).","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"1458_CR45","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In NeurIPS (pp. 3111\u20133119)."},{"key":"1458_CR46","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., & Deng, J. (2016). Stacked hourglass networks for human pose estimation. In ECCV (pp. 483\u2013499).","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1458_CR47","doi-asserted-by":"crossref","unstructured":"Oomoto, K., Oikawa, H., Yamamoto, E., Yoshida, M., Okabe, M., & Umemura, K. (2017). Polysemy detection in distributed representation of word sense. In KST (pp. 28\u201333).","DOI":"10.1109\/KST.2017.7886073"},{"issue":"12","key":"1458_CR48","doi-asserted-by":"publisher","first-page":"2914","DOI":"10.1109\/TMI.2019.2918096","volume":"38","author":"S Pereira","year":"2019","unstructured":"Pereira, S., Pinto, A., Amorim, J., Ribeiro, A., Alves, V., & Silva, C. A. (2019). Adaptive feature recombination and recalibration for semantic segmentation with fully convolutional networks. IEEE Transactions on Medical Imaging, 38(12), 2914\u20132925.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"1458_CR49","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de Vries, H., Dumoulin, V., & Courville, A. (2018). FiLM: Visual reasoning with a general conditioning layer. In AAAI.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"1458_CR50","doi-asserted-by":"crossref","unstructured":"Peyre, J., Laptev, I., Schmid, C., & Sivic, J. (2019). Detecting unseen visual relations using analogies. In ICCV (pp. 1981\u20131990).","DOI":"10.1109\/ICCV.2019.00207"},{"key":"1458_CR51","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., & Zhu, S.C. (2018). Learning human\u2013object interactions by graph parsing neural networks. In ECCV (pp. 401\u2013417).","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"1458_CR52","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In NeurIPS (pp. 91\u201399)."},{"key":"1458_CR53","doi-asserted-by":"crossref","unstructured":"Shen, L., Yeung, S., Hoffman, J., Mori, G., & Li, F. (2018). Scaling human\u2013object interaction recognition through zero-shot learning. In WACV (pp. 1568\u20131576).","DOI":"10.1109\/WACV.2018.00181"},{"key":"1458_CR54","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In NeurIPS (pp. 568\u2013576)."},{"key":"1458_CR55","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. In ICCV (pp. 4489\u20134497).","DOI":"10.1109\/ICCV.2015.510"},{"key":"1458_CR56","doi-asserted-by":"crossref","unstructured":"Ulutan, O., Iftekhar, A., & Manjunath, B. (2020). Vsgnet: Spatial attention network for detecting human object interactions using graph convolutions. In CVPR (pp. 13617\u201313626).","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"1458_CR57","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., & Gomez, A., (2017). Attention is all you need. In NeurIPS (pp. 5998\u20136008)."},{"key":"1458_CR58","doi-asserted-by":"crossref","unstructured":"Wan, B., Zhou, D., Liu, Y., Li, R., & He, X. (2019). Pose-aware multi-level feature network for human object interaction detection. In ICCV (pp. 9469\u20139478).","DOI":"10.1109\/ICCV.2019.00956"},{"key":"1458_CR59","doi-asserted-by":"crossref","unstructured":"Wang, T., Anwer, RM., Khan, MH., Khan, FS., Pang, Y., Shao, L., & Laaksonen, J. (2019a). Deep contextual attention for human\u2013object interaction detection. In ICCV (pp. 5694\u20135702).","DOI":"10.1109\/ICCV.2019.00579"},{"key":"1458_CR60","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017). Residual attention network for image classification. In CVPR (pp. 3156\u20133164).","DOI":"10.1109\/CVPR.2017.683"},{"key":"1458_CR61","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, R., Shan, S., & Chen, X. (2019b). Exploring context and visual pattern of relationship for scene graph generation. In CVPR (pp. 8188\u20138197).","DOI":"10.1109\/CVPR.2019.00838"},{"key":"1458_CR62","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, FS., Zhang, X., & Sun, J. (2020). Learning human\u2013object interaction detection using interaction points. In CVPR (pp. 4116\u20134125).","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"1458_CR63","first-page":"1784","volume":"30","author":"N Wang","year":"2021","unstructured":"Wang, N., Zhang, Y., & Zhang, L. (2021). Dynamic selection network for image inpainting. TIP, 30, 1784\u20131798.","journal-title":"TIP"},{"key":"1458_CR64","unstructured":"Xu, K., Ba, J, Kiros, R, Cho, K, Courville, A., Salakhudinov, R., Zemel, R., & Bengio, Y. (2015). Show, attend and tell: Neural image caption generation with visual attention. In ICML (pp. 2048\u20132057)."},{"key":"1458_CR65","doi-asserted-by":"crossref","unstructured":"Xu, B., Wong, Y., Li, J., Zhao, Q., & Kankanhalli, M.S. (2019). Learning to detect human\u2013object interactions with knowledge. In CVPR (pp. 2019\u20132028).","DOI":"10.1109\/CVPR.2019.00212"},{"issue":"6","key":"1458_CR66","first-page":"1423","volume":"22","author":"B Xu","year":"2020","unstructured":"Xu, B., Li, J., Wong, Y., Zhao, Q., & Kankanhalli, M. S. (2020). Interact as you intend: Intention-driven human-object interaction detection. TMM, 22(6), 1423\u20131432.","journal-title":"TMM"},{"key":"1458_CR67","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., & Mei, T. (2019). Hierarchy parsing for image captioning. arXiv:1909.03918.","DOI":"10.1109\/ICCV.2019.00271"},{"key":"1458_CR68","doi-asserted-by":"crossref","unstructured":"Ye, Q., Yuan, S., & Kim, T. (2016). Spatial attention deep net with partial pso for hierarchical hybrid hand pose estimation. In ECCV (pp. 346\u2013361).","DOI":"10.1007\/978-3-319-46484-8_21"},{"key":"1458_CR69","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., & Luo, J. (2016). Image captioning with semantic attention. In CVPR (pp. 4651\u20134659).","DOI":"10.1109\/CVPR.2016.503"},{"key":"1458_CR70","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., & Choi, Y. (2018). Neural motifs: Scene graph parsing with global context. In CVPR (pp. 5831\u20135840).","DOI":"10.1109\/CVPR.2018.00611"},{"key":"1458_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, SF., & Chua, T.S. (2017). Visual translation embedding network for visual relation detection. In CVPR (pp. 5532\u20135540).","DOI":"10.1109\/CVPR.2017.331"},{"issue":"1","key":"1458_CR72","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s11263-019-01211-2","volume":"128","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., & Lin, D. (2020). Temporal action detection with structured segment networks. IJCV, 128(1), 74\u201395.","journal-title":"IJCV"},{"issue":"2","key":"1458_CR73","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s11263-014-0795-4","volume":"112","author":"B Zheng","year":"2015","unstructured":"Zheng, B., Zhao, Y., Yu, J., Ikeuchi, K., & Zhu, S. C. (2015). Scene understanding by reasoning stability and safety. IJCV, 112(2), 221\u2013238.","journal-title":"IJCV"},{"key":"1458_CR74","doi-asserted-by":"crossref","unstructured":"Zhong, X., Ding, C., Qu, X., & Tao, D. (2020). Polysemy deciphering network for human\u2013object interaction detection. In ECCV (pp. 69-85).","DOI":"10.1007\/978-3-030-58565-5_5"},{"key":"1458_CR75","doi-asserted-by":"crossref","unstructured":"Zhong, X., Qu, X., Ding, C., & Tao, D. (2021). Glance and Gaze: Inferring action-aware points for one-stage human\u2013object interaction detection. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"1458_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, P., & Chi, M. (2019). Relation parsing neural network for human\u2013object interaction detection. In ICCV (pp. 843\u2013851).","DOI":"10.1109\/ICCV.2019.00093"},{"key":"1458_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., & Gao, J. (2019). Unified vision-language pre-training for image captioning and VQA. arXiv:1909.11059.","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"1458_CR78","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019b). Objects as points. arXiv:1904.07850."},{"key":"1458_CR79","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Qi, S., Ling, H., & Shen, J. (2020). Cascaded human\u2013object interaction recognition. In CVPR (pp. 4263\u20134272).","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"1458_CR80","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., & Hengel, Avd. (2017). Care about you: towards large-scale human-centric visual relationship detection. arXiv:1705.09892."},{"issue":"1","key":"1458_CR81","first-page":"113","volume":"28","author":"Y Zhu","year":"2018","unstructured":"Zhu, Y., Zhao, C., Guo, H., Wang, J., Zhao, X., & Lu, H. (2018). Attention couplenet: Fully convolutional attention coupling network for object detection. TIP, 28(1), 113\u2013126.","journal-title":"TIP"},{"key":"1458_CR82","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., & Le, Q.V. (2018). Learning transferable architectures for scalable image recognition. In CVPR (pp. 8697\u20138710).","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01458-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01458-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01458-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T16:55:34Z","timestamp":1671900934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01458-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":82,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["1458"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01458-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,19]]},"assertion":[{"value":"1 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}