{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:24:32Z","timestamp":1791393872764,"version":"4.3.3"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research & Development Project of China","award":["021ZD0110700"],"award-info":[{"award-number":["021ZD0110700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62337001"],"award-info":[{"award-number":["62337001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No. 226-2022-00051"],"award-info":[{"award-number":["No. 226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HKUST Special Support for Young Faculty","award":["F0927"],"award-info":[{"award-number":["F0927"]}]},{"name":"HKUST Sports Science and Technology Research Grant","award":["SSTRG24EG04"],"award-info":[{"award-number":["SSTRG24EG04"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11263-024-02190-9","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T16:47:26Z","timestamp":1722876446000},"page":"489-508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["From Easy to Hard: Learning Curricular Shape-Aware Features for Robust Panoptic Scene Graph Generation"],"prefix":"10.1007","volume":"133","author":[{"given":"Hanrong","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,5]]},"reference":[{"key":"2190_CR1","first-page":"41","volume":"382","author":"Y Bengio","year":"2009","unstructured":"Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. ICML, ACM International Conference Proceeding Series, 382, 41\u201348.","journal-title":"ICML, ACM International Conference Proceeding Series"},{"key":"2190_CR2","doi-asserted-by":"crossref","unstructured":"Cao, J., Leng, H., Lischinski, D., Cohen-Or, D., Tu, C., & Li, Y. (2021a) Shapeconv: Shape-aware convolutional layer for indoor RGB-D semantic segmentation. In ICCV (pp. 7068\u20137077).","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"2190_CR3","doi-asserted-by":"crossref","unstructured":"Cao, M., Chen, L., Shou, M. Z., Zhang, C., & Zou, Y. (2021b) On pursuit of designing multi-modal transformer for video grounding. In EMNLP (pp. 9810\u20139823).","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"2190_CR4","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume":"12346","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. ECCV, Lecture Notes in Computer Science, 12346, 213\u2013229.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"key":"2190_CR5","unstructured":"Chen, G., &Wang, W. (2024) A survey on 3d gaussian splatting. CoRR arXiv:abs\/2401.03890"},{"key":"2190_CR6","doi-asserted-by":"crossref","unstructured":"Chen, G., Li, L., Luo, Y., & Xiao, J. (2023) Addressing predicate overlap in scene graph generation with semantic granularity controller. In ICME (pp. 78\u201383).","DOI":"10.1109\/ICME55011.2023.00022"},{"key":"2190_CR7","doi-asserted-by":"crossref","unstructured":"Chen, G., Li, X., Yang, Y., &Wang, W. (2024) Neural clustering based visual representation learning. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00546"},{"key":"2190_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., He, X., Pu, S., & Chang, S. (2019) Counterfactual critic multi-agent training for scene graph generation. In ICCV (pp. 4612\u20134622).","DOI":"10.1109\/ICCV.2019.00471"},{"key":"2190_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., & Girdhar, R. (2022) Masked-attention mask transformer for universal image segmentation. In CVPR (pp. 1280\u20131289).","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2190_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Liu, A. Q., Magnenat-Thalmann, N., & Wang, G. (2019) Boundary-aware feature propagation for scene segmentation. In ICCV (pp. 6818\u20136828).","DOI":"10.1109\/ICCV.2019.00692"},{"key":"2190_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., Gan, T., Song, X., Wu, J., Cheng, Y., & Nie, L. (2022) Stacked hybrid-attention and group collaborative learning for unbiased scene graph generation. In CVPR (pp. 19405\u201319414).","DOI":"10.1109\/CVPR52688.2022.01882"},{"issue":"7","key":"2190_CR12","doi-asserted-by":"publisher","first-page":"2057","DOI":"10.1007\/s11263-021-01471-x","volume":"129","author":"TL Gomes","year":"2021","unstructured":"Gomes, T. L., Martins, R., Ferreira, J., Azevedo, R., Torres, G., & Nascimento, E. R. (2021). A shape-aware retargeting approach to transfer human motion and appearance in monocular videos. IJCV, 129(7), 2057\u20132075.","journal-title":"IJCV"},{"key":"2190_CR13","doi-asserted-by":"crossref","unstructured":"Gong, J., Xu, J., Tan, X., Zhou, J., Qu, Y., Xie, Y., & Ma, L. (2021) Boundary-aware geometric encoding for semantic segmentation of point clouds. In AAAI (pp. 1424\u20131432).","DOI":"10.1609\/aaai.v35i2.16232"},{"key":"2190_CR14","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01249-6_9","volume":"11214","author":"S Guo","year":"2018","unstructured":"Guo, S., Huang, W., Zhang, H., Zhuang, C., Dong, D., Scott, M. R., & Huang, D. (2018). Curriculumnet: Weakly supervised learning from large-scale web images. ECCV, Lecture Notes in Computer Science, 11214, 139\u2013154.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"key":"2190_CR15","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":"2190_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. B. (2017) Mask R-CNN. In ICCV (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2190_CR17","first-page":"43","volume":"32","author":"T He","year":"2022","unstructured":"He, T., Gao, L., Song, J., & Li, Y. F. (2022). State-aware compositional learning toward unbiased training for scene graph generation. TIP, 32, 43\u201356.","journal-title":"TIP"},{"key":"2190_CR18","doi-asserted-by":"crossref","unstructured":"Hu, H., Cui, J., &Zha, H. (2020) Boundary-aware graph convolution for semantic segmentation. In ICPR (pp. 1828\u20131835).","DOI":"10.1109\/ICPR48806.2021.9412034"},{"key":"2190_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Zhao, Q., Shan, S., & Hauptmann, A. G. (2015) Self-paced curriculum learning. In AAAI (pp. 2694\u20132700).","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"2190_CR20","doi-asserted-by":"crossref","unstructured":"Jin, T., Guo, F., Meng, Q., Zhu, S., Xi, X., Wang, W., Mu, Z., & Song, W. (2023) Fast contextual scene graph generation with unbiased context augmentation. In CVPR (pp. 6302\u20136311).","DOI":"10.1109\/CVPR52729.2023.00610"},{"issue":"4","key":"2190_CR21","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1007\/s11263-022-01736-z","volume":"131","author":"SS Jinka","year":"2023","unstructured":"Jinka, S. S., Srivastava, A., Pokhariya, C., Sharma, A., & Narayanan, P. (2023). Sharp: Shape-aware reconstruction of people in loose clothing. IJCV, 131(4), 918\u2013937.","journal-title":"IJCV"},{"key":"2190_CR22","doi-asserted-by":"crossref","unstructured":"Jung, D., Kim, S., Kim, W. H., & Cho, M. (2023) Devil\u2019s on the edges: Selective quad attention for scene graph generation. In CVPR (pp. 18664\u201318674).","DOI":"10.1109\/CVPR52729.2023.01790"},{"key":"2190_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R. B., Rother, C., & Doll\u00e1r, P. (2019) Panoptic segmentation. In CVPR (pp. 9404\u20139413).","DOI":"10.1109\/CVPR.2019.00963"},{"key":"2190_CR24","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W., Doll\u00e1r, P., & Girshick, R. B. (2023) Segment anything. In ICCV (pp. 3992\u20134003).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2190_CR25","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback, S., & Leibler, R. A. (1951). On information and sufficiency. Annals of Mathematical Statistics, 22, 79\u201386.","journal-title":"Annals of Mathematical Statistics"},{"key":"2190_CR26","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, L., Liu, P., & Yang, Y. (2019a) Entangled transformer for image captioning. In ICCV (pp. 8927\u20138936).","DOI":"10.1109\/ICCV.2019.00902"},{"issue":"2","key":"2190_CR27","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1109\/TPAMI.2023.3327677","volume":"46","author":"G Li","year":"2024","unstructured":"Li, G., Ye, H., Qi, Y., Wang, S., Qing, L., Huang, Q., & Yang, M. H. (2024). Learning hierarchical modular networks for video captioning. TPAMI, 46(2), 1049\u20131064.","journal-title":"TPAMI"},{"key":"2190_CR28","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., & Xiao, J. (2022a) The devil is in the labels: Noisy label correction for robust scene graph generation. In CVPR (pp. 18847\u201318856).","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"2190_CR29","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, G., Xiao, J., Yang, Y., Wang, C., & Chen, L. (2023a) Compositional feature augmentation for unbiased scene graph generation. In ICCV (pp. 21628\u201321638).","DOI":"10.1109\/ICCV51070.2023.01982"},{"key":"2190_CR30","unstructured":"Li, L., Ji, W., Wu, Y., Li, M., Qin, Y., Wei, L., & Zimmermann, R. (2023b) Panoptic scene graph generation with semantics-prototype learning. CoRR arXiv:abs\/2307.15567"},{"key":"2190_CR31","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, C., Qin, Y., Ji, W., & Liang, R. (2023c) Biased-predicate annotation identification via unbiased visual predicate representation. In MM (pp. 4410\u20134420).","DOI":"10.1145\/3581783.3611847"},{"key":"2190_CR32","unstructured":"Li, L., Xiao, J., Chen, G., Shao, J., Zhuang, Y., & Chen, L. (2023d) Zero-shot visual relation detection via composite visual cues from large language models. In NIPS (pp. 50105\u201350116)."},{"key":"2190_CR33","doi-asserted-by":"crossref","unstructured":"Li, L., Qin, Y., Ji, W., Zhou, Y., & Zimmermann, R. (2024b) Domain-wise invariant learning for panoptic scene graph generation. In ICASSP (pp. 3165\u20133169).","DOI":"10.1109\/ICASSP48485.2024.10447193"},{"issue":"1","key":"2190_CR34","first-page":"195","volume":"34","author":"L Li","year":"2024","unstructured":"Li, L., Xiao, J., Shi, H., Wang, W., Shao, J., Liu, A., Yang, Y., & Chen, L. (2024). Label semantic knowledge distillation for unbiased scene graph generation. TCSVT, 34(1), 195\u2013206.","journal-title":"TCSVT"},{"key":"2190_CR35","doi-asserted-by":"crossref","unstructured":"Li, L., Xiao, J., Shi, H., Zhang, H., Yang, Y., Liu, W., & Chen, L. (2024d) NICEST: noisy label correction and training for robust scene graph generation. In TPAMI.","DOI":"10.1109\/TPAMI.2024.3387349"},{"key":"2190_CR36","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., Wan, B., & He, X. (2021) Bipartite graph network with adaptive message passing for unbiased scene graph generation. In CVPR (pp. 11109\u201311119).","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"2190_CR37","doi-asserted-by":"crossref","unstructured":"Li, X., Chen, L., Ma, W., Yang, Y., & Xiao, J. (2022b) Integrating object-aware and interaction-aware knowledge for weakly supervised scene graph generation. In MM (pp. 4204\u20134213).","DOI":"10.1145\/3503161.3548164"},{"key":"2190_CR38","volume":"89","author":"X Li","year":"2023","unstructured":"Li, X., Luo, G., Wang, W., Wang, K., & Li, S. (2023). Curriculum label distribution learning for imbalanced medical image segmentation. Media, 89, 102911.","journal-title":"Media"},{"issue":"9","key":"2190_CR39","doi-asserted-by":"publisher","first-page":"2070","DOI":"10.1109\/TPAMI.2018.2852750","volume":"41","author":"Z Li","year":"2019","unstructured":"Li, Z., Tang, J., & Mei, T. (2019). Deep collaborative embedding for social image understanding. TPAMI, 41(9), 2070\u20132083.","journal-title":"TPAMI"},{"key":"2190_CR40","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Xie, E., Yu, Z., Anandkumar, A., \u00c1lvarez, J. M., Luo, P., & Lu, T. (2022c) Panoptic segformer: Delving deeper into panoptic segmentation with transformers. In CVPR (pp. 1270\u20131279).","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"2190_CR41","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume":"8693","author":"T Lin","year":"2014","unstructured":"Lin, T., Maire, M., Belongie, S. J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. ECCV, Lecture Notes in Computer Science, 8693, 740\u2013755.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"key":"2190_CR42","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. 3743\u20133752).","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"2190_CR43","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume":"9905","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M. S., & Fei-Fei, L. (2016). Visual relationship detection with language priors. ECCV, Lecture Notes in Computer Science, 9905, 852\u2013869.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"key":"2190_CR44","doi-asserted-by":"crossref","unstructured":"Lu, Y., Rai, H., Chang, J., Knyazev, B., Yu, G. W., Shekhar, S., Taylor, G. W., & Volkovs, M. (2021) Context-aware scene graph generation with seq2seq transformers. In ICCV (pp. 15911\u201315921).","DOI":"10.1109\/ICCV48922.2021.01563"},{"issue":"11","key":"2190_CR45","first-page":"13921","volume":"45","author":"X Lyu","year":"2023","unstructured":"Lyu, X., Gao, L., Zeng, P., Shen, H. T., & Song, J. (2023). Adaptive fine-grained predicates learning for scene graph generation. TPAMI, 45(11), 13921\u201313940.","journal-title":"TPAMI"},{"issue":"3","key":"2190_CR46","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1364\/JOSA.66.000207","volume":"66","author":"RJ Noll","year":"1976","unstructured":"Noll, R. J. (1976). Zernike polynomials and atmospheric turbulence. JOsA, 66(3), 207\u2013211.","journal-title":"JOsA"},{"issue":"6441","key":"2190_CR47","doi-asserted-by":"publisher","first-page":"eaav8911","DOI":"10.1126\/science.aav8911","volume":"364","author":"M Sarafyazd","year":"2019","unstructured":"Sarafyazd, M., & Jazayeri, M. (2019). Hierarchical reasoning by neural circuits in the frontal cortex. Science, 364(6441), eaav8911.","journal-title":"Science"},{"issue":"6","key":"2190_CR48","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1007\/s11263-022-01611-x","volume":"30","author":"P Soviany","year":"2022","unstructured":"Soviany, P., Ionescu, R. T., Rota, P., & Sebe, N. (2022). Curriculum learning: A survey. IJCV, 30(6), 1526\u20131565.","journal-title":"IJCV"},{"issue":"8","key":"2190_CR49","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.1109\/TPAMI.2016.2608882","volume":"39","author":"J Tang","year":"2017","unstructured":"Tang, J., Shu, X., Qi, G., Li, Z., Wang, M., Yan, S., & Jain, R. C. (2017). Tri-clustered tensor completion for social-aware image tag refinement. TPAMI, 39(8), 1662\u20131674.","journal-title":"TPAMI"},{"key":"2190_CR50","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., & Liu, W. (2019) Learning to compose dynamic tree structures for visual contexts. In CVPR (pp. 6619\u20136628).","DOI":"10.1109\/CVPR.2019.00678"},{"key":"2190_CR51","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., & Zhang, H. (2020) Unbiased scene graph generation from biased training. In CVPR (pp. 3713\u20133722).","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"2190_CR52","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shu, M., Lyu, P., Li, R., Zhou, C., Shen, X., & Jia, J. (2019) Learning shape-aware embedding for scene text detection. In CVPR (pp. 4234\u20134243).","DOI":"10.1109\/CVPR.2019.00436"},{"issue":"7","key":"2190_CR53","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/S0031-8914(34)80259-5","volume":"1","author":"F von Zernike","year":"1934","unstructured":"von Zernike, F. (1934). Beugungstheorie des schneidenver-fahrens und seiner verbesserten form, der phasenkontrastmethode. Physica, 1(7), 689\u2013704.","journal-title":"Physica"},{"key":"2190_CR54","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) Attention is all you need. In NIPS (pp. 5998\u20136008)."},{"issue":"11","key":"2190_CR55","doi-asserted-by":"publisher","first-page":"3074","DOI":"10.1007\/s11263-023-01851-5","volume":"131","author":"J Wang","year":"2023","unstructured":"Wang, J., Chen, Z., Yuan, C., Li, B., Ma, W., & Hu, W. (2023). Hierarchical curriculum learning for no-reference image quality assessment. IJCV, 131(11), 3074\u20133093.","journal-title":"IJCV"},{"key":"2190_CR56","unstructured":"Wang, J., Wen, Z., Li, X., Guo, Z., Yang, J., & Liu, Z. (2023b) Pair then relation: Pair-net for panoptic scene graph generation. CoRR arXiv:abs\/2307.08699"},{"issue":"9","key":"2190_CR57","doi-asserted-by":"crossref","first-page":"4555","DOI":"10.1109\/TPAMI.2021.3072422","volume":"44","author":"X Wang","year":"2022","unstructured":"Wang, X., Chen, Y., & Zhu, W. (2022). A survey on curriculum learning. TPAMI, 44(9), 4555\u20134576.","journal-title":"TPAMI"},{"key":"2190_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y., Gan, W., Yang, J., Wu, W., & Yan, J. (2019) Dynamic curriculum learning for imbalanced data classification. In ICCV (pp. 5016\u20135025).","DOI":"10.1109\/ICCV.2019.00512"},{"key":"2190_CR59","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, CB., & Fei-Fei, L. (2017) Scene graph generation by iterative message passing. In CVPR (pp. 3097\u20133106).","DOI":"10.1109\/CVPR.2017.330"},{"key":"2190_CR60","doi-asserted-by":"crossref","unstructured":"Xu, J., Chen, J., & Yanai, K. (2023a) Contextual associated triplet queries for panoptic scene graph generation. In MMAsia (pp. 100:1\u2013100:5).","DOI":"10.1145\/3595916.3626745"},{"issue":"12","key":"2190_CR61","doi-asserted-by":"publisher","first-page":"3272","DOI":"10.1007\/s11263-023-01850-6","volume":"131","author":"X Xu","year":"2023","unstructured":"Xu, X., Li, Y., & Lu, C. (2023). Dynamic context removal: A general training strategy for robust models on video action predictive tasks. IJCV, 131(12), 3272\u20133288.","journal-title":"IJCV"},{"key":"2190_CR62","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-031-19812-0_11","volume":"13687","author":"J Yang","year":"2022","unstructured":"Yang, J., Ang, Y. Z., Guo, Z., Zhou, K., Zhang, W., & Liu, Z. (2022). Panoptic scene graph generation. ECCV, Lecture Notes in Computer Science, 13687, 178\u2013196.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"key":"2190_CR63","doi-asserted-by":"crossref","unstructured":"Yang, J., Wang, C., Liu, Z., Wu, J., Wang, D., Yang, L., & Cao, X. (2023a) Focusing on flexible masks: A novel framework for panoptic scene graph generation with relation constraints. In MM (pp. 4209\u20134218).","DOI":"10.1145\/3581783.3612544"},{"issue":"5","key":"2190_CR64","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1007\/s11263-023-01748-3","volume":"131","author":"X Yang","year":"2023","unstructured":"Yang, X., Burghardt, T., & Mirmehdi, M. (2023). Dynamic curriculum learning for great ape detection in the wild. IJCV, 131(5), 1163\u20131181.","journal-title":"IJCV"},{"key":"2190_CR65","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., & Wu, Q. (2021) Cogtree: Cognition tree loss for unbiased scene graph generation. In IJCAI (pp. 1274\u20131280).","DOI":"10.24963\/ijcai.2021\/176"},{"key":"2190_CR66","doi-asserted-by":"crossref","unstructured":"Yu, Q., Li, J., Wu ,Y., Tang, S., Ji, W., & Zhuang, Y. (2023) Visually-prompted language model for fine-grained scene graph generation in an open world. In ICCV (pp. 21503\u201321514).","DOI":"10.1109\/ICCV51070.2023.01971"},{"key":"2190_CR67","first-page":"1","volume":"60","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., Mou, L., Wang, Q., & Zhu, X. X. (2022). From easy to hard: Learning language-guided curriculum for visual question answering on remote sensing data. TGRS, 60, 1\u201311.","journal-title":"TGRS"},{"key":"2190_CR68","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/978-3-030-58592-1_38","volume":"12368","author":"A Zareian","year":"2020","unstructured":"Zareian, A., Wang, Z., You, H., & Chang, S. (2020). Learning visual commonsense for robust scene graph generation. ECCV, Lecture Notes in Computer Science, 12368, 642\u2013657.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"key":"2190_CR69","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":"2190_CR70","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/978-3-031-19812-0_24","volume":"13687","author":"A Zhang","year":"2022","unstructured":"Zhang, A., Yao, Y., Chen, Q., Ji, W., Liu, Z., Sun, M., & Chua, T. (2022). Fine-grained scene graph generation with data transfer. ECCV, Lecture Notes in Computer Science, 13687, 409\u2013424.","journal-title":"ECCV, Lecture Notes in Computer Science"},{"issue":"4","key":"2190_CR71","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/s11263-018-1112-4","volume":"127","author":"D Zhang","year":"2019","unstructured":"Zhang, D., Han, J., Zhao, L., & Meng, D. (2019). Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework. IJCV, 127(4), 363\u2013380.","journal-title":"IJCV"},{"key":"2190_CR72","first-page":"655","volume":"33","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Zhang, H., Tang, J., Hua, X., & Sun, Q. (2020). Causal intervention for weakly-supervised semantic segmentation. NIPS, 33, 655\u2013666.","journal-title":"NIPS"},{"key":"2190_CR73","doi-asserted-by":"crossref","unstructured":"Zhao, L., Yuan, L., Gong, B., Cui, Y., Schroff, F., Yang, M., Adam, H., &Liu, T. (2023) Unified visual relationship detection with vision and language models. In ICCV, IEEE (pp. 6939\u20136950).","DOI":"10.1109\/ICCV51070.2023.00641"},{"key":"2190_CR74","doi-asserted-by":"crossref","unstructured":"Zheng, C., Lyu, X., Gao, L., Dai, B., & Song, J. (2023) Prototype-based embedding network for scene graph generation. In CVPR (pp. 22783\u201322792).","DOI":"10.1109\/CVPR52729.2023.02182"},{"issue":"3","key":"2190_CR75","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., & Torralba, A. (2019). Semantic understanding of scenes through the ade20k dataset. IJCV, 127(3), 302\u2013321.","journal-title":"IJCV"},{"key":"2190_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Shi, M., &Caesar, H. (2023) Hilo: Exploiting high low frequency relations for unbiased panoptic scene graph generation. In ICCV (pp. 21580\u201321591).","DOI":"10.1109\/ICCV51070.2023.01978"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02190-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02190-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02190-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T06:17:29Z","timestamp":1736230649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02190-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":76,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2190"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02190-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,5]]},"assertion":[{"value":"15 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}