{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T08:49:38Z","timestamp":1782809378319,"version":"3.54.5"},"reference-count":48,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Basic Research Program of Jiangsu","award":["BK20251025"],"award-info":[{"award-number":["BK20251025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Images captured by vision sensors provide visual evidence for scene understanding, including object appearances, pixel-level regions, and spatial relations among entities. Panoptic Scene Graph Generation (PSG) constructs structured scene representations by grounding visual entities with panoptic masks and predicting relationships among objects and regions. In pair-then-relation PSG pipelines, subject\u2013object pair recall is critical to final triplet recall. However, existing pair proposal approaches mainly score candidate subject\u2013object pairs based on object\u2013query feature matching, while mask-derived spatial cues such as object locations, relative geometry, and local layouts remain underexplored. Consequently, ground-truth subject\u2013object pairs may be excluded from the Top-Kr proposals before relation decoding. To address this problem, this paper proposes a Spatially Aware Pair Proposal Model (SAPPM), which incorporates mask-derived soft centroids, relative geometry, and local-neighborhood context into pair scoring. SAPPM uses Grouped Vector Attention (GVA) to model local spatial interactions and introduces a spatially adaptive gating module to calibrate spatial-branch contributions. Experiments on the PSG dataset under the Scene Graph Detection (SGDet) protocol show that SAPPM achieves competitive performance, reaching 32.53 R@20 and 27.36 mR@20. These results indicate that SAPPM improves PSG performance by enhancing ground-truth pair coverage in the candidate proposal set.<\/jats:p>","DOI":"10.3390\/s26134119","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T08:26:15Z","timestamp":1782807975000},"page":"4119","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatially Aware Pair Proposal for Panoptic Scene Graph Generation"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8022-7843","authenticated-orcid":false,"given":"Hanzhu","family":"Dai","sequence":"first","affiliation":[{"name":"College of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, China"},{"name":"Systems Science Laboratory, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8324-6708","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, China"},{"name":"Systems Science Laboratory, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8395-1532","authenticated-orcid":false,"given":"Binghao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, China"},{"name":"Systems Science Laboratory, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8851-9179","authenticated-orcid":false,"given":"Mai","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Yang, W., Qiu, H., Luo, X., and Xie, S. (2024). SGK-Net: A Novel Navigation Scene Graph Generation Network. Sensors, 24.","DOI":"10.3390\/s24134329"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., and Li, F.-F. (2017, January 21\u201326). Scene Graph Generation by Iterative Message Passing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"108245","DOI":"10.1016\/j.knosys.2022.108245","article-title":"roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs","volume":"242","author":"Malawade","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Singh, K.P., Salvador, J., Weihs, L., and Kembhavi, A. (2023, January 1\u20136). Scene Graph Contrastive Learning for Embodied Navigation. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00999"},{"key":"ref_5","unstructured":"Zhu, Y., Tremblay, J., Birchfield, S., and Zhu, Y. (June, January 30). Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Xi\u2019an, China."},{"key":"ref_6","unstructured":"Patel, T., Yao, A.Y.H., Qiang, Y., Ooi, W.T., and Zimmermann, R. (2021, January 19\u201322). Multi-Camera Video Scene Graphs for Surveillance Videos Indexing and Retrieval. Proceedings of the IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tian, Y., Carballo, A., Li, R., Thompson, S., and Takeda, K. (2025). Query by Example: Semantic Traffic Scene Retrieval Using LLM-Based Scene Graph Representation. Sensors, 25.","DOI":"10.3390\/s25082546"},{"key":"ref_8","first-page":"178","article-title":"Panoptic Scene Graph Generation","volume":"Volume 13687","author":"Avidan","year":"2022","journal-title":"Computer Vision\u2014ECCV 2022"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"10452","DOI":"10.1109\/TPAMI.2024.3442301","article-title":"Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","first-page":"3145","article-title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","volume":"38","author":"Li","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Shi, M., and Caesar, H. (2023, January 1\u20136). HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01978"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1007\/s11263-024-02190-9","article-title":"From Easy to Hard: Learning Curricular Shape-Aware Features for Robust Panoptic Scene Graph Generation","volume":"133","author":"Shi","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"ref_13","unstructured":"Yang, J., Wang, C., Liu, Z., Wu, J., Wang, D., Yang, L., and Cao, X. (November, January 29). Focusing on Flexible Masks: A Novel Framework for Panoptic Scene Graph Generation with Relation Constraints. Proceedings of the ACM International Conference on Multimedia (ACM MM), Ottawa, ON, Canada."},{"key":"ref_14","first-page":"199","article-title":"OpenPSG: Open-Set Panoptic Scene Graph Generation via Large Multimodal Models","volume":"Volume 15068","author":"Leonardis","year":"2025","journal-title":"Computer Vision\u2014ECCV 2024"},{"key":"ref_15","first-page":"148","article-title":"A Fair Ranking and New Model for Panoptic Scene Graph Generation","volume":"Volume 15119","author":"Leonardis","year":"2025","journal-title":"Computer Vision\u2014ECCV 2024"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"8006","DOI":"10.1007\/s11263-025-02564-7","article-title":"VLPrompt-PSG: Vision-Language Prompting for Panoptic Scene Graph Generation","volume":"133","author":"Zhou","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100394","DOI":"10.1016\/j.array.2025.100394","article-title":"DGTM: Deriving Graph from Transformer with Mamba for Panoptic Scene Graph Generation","volume":"26","author":"Sun","year":"2025","journal-title":"Array"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1007\/s40747-024-01746-z","article-title":"Semantic-Enhanced Panoptic Scene Graph Generation Through Hybrid and Axial Attentions","volume":"11","author":"Kuang","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","article-title":"Visual Relationship Detection with Language Priors","volume":"Volume 9905","author":"Leibe","year":"2016","journal-title":"Computer Vision\u2014ECCV 2016"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"Int. J. Comput. Vis."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., and Chua, T.S. (2017, January 21\u201326). Visual Translation Embedding Network for Visual Relation Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., and Lin, D. (2017, January 21\u201326). Detecting Visual Relationships with Deep Relational Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., and Wang, X. (2017, January 22\u201329). Scene Graph Generation from Objects, Phrases and Region Captions. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., and Choi, Y. (2018, January 18\u201323). Neural Motifs: Scene Graph Parsing with Global Context. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., and Liu, W. (2019, January 16\u201320). Learning to Compose Dynamic Tree Structures for Visual Contexts. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., and Lin, L. (2019, January 16\u201320). Knowledge-Embedded Routing Network for Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00632"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., and Tao, D. (2020, January 14\u201319). GPS-Net: Graph Property Sensing Network for Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., and He, X. (2022, January 18\u201324). SGTR: End-to-End Scene Graph Generation with Transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"11169","DOI":"10.1109\/TPAMI.2023.3268066","article-title":"RelTR: Relation Transformer for Scene Graph Generation","volume":"45","author":"Cong","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, H., Yan, N., Mortazavi, M., and Bhanu, B. (2021, January 20\u201325). Fully Convolutional Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Im, J., Nam, J., Park, N., Lee, H., and Park, S. (2024, January 16\u201322). EGTR: Extracting Graph from Transformer for Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hayder, Z., and He, X. (2024, January 16\u201322). DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02675"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., and Zhang, H. (2020, January 14\u201319). Unbiased Scene Graph Generation from Biased Training. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., Wan, B., and He, X. (2021, January 20\u201325). Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., and Wu, Q. (2021, January 19\u201327). CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Montreal, QC, Canada.","DOI":"10.24963\/ijcai.2021\/176"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Desai, A., Wu, T.Y., Tripathi, S., and Vasconcelos, N. (2021, January 10\u201317). Learning of Visual Relations: The Devil Is in the Tails. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, L., Huang, Y., Zhang, Z., Zhang, S., and Xiao, J. (2022, January 18\u201324). The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Jung, D., Kim, S., Kim, W.H., and Cho, M. (2023, January 17\u201324). Devil\u2019s on the Edges: Selective Quad Attention for Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01790"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, J., Elhoseiny, M., Cohen, S., Chang, W., and Elgammal, A. (2017, January 21\u201326). Relationship Proposal Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.555"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1007\/978-3-030-01246-5_41","article-title":"Graph R-CNN for Scene Graph Generation","volume":"Volume 11205","author":"Ferrari","year":"2018","journal-title":"Computer Vision\u2014ECCV 2018"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Teng, Y., and Wang, L. (2022, January 18\u201324). Structured Sparse R-CNN for Direct Scene Graph Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01883"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., and He, K. (2018, January 18\u201323). Non-Local Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 10\u201317). Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_44","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2021, January 3\u20137). Deformable DETR: Deformable Transformers for End-to-End Object Detection. Proceedings of the 9th International Conference on Learning Representations (ICLR 2021), Virtual Event, Austria. Available online: https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke."},{"key":"ref_45","unstructured":"Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., and Garnett, R. (2017). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Advances in Neural Information Processing Systems 30: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 4\u20139 December 2017, Curran Associates, Inc.. Available online: https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/d8bf84be3800d12f74d8b05e9b89836f-Abstract.html."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H.S., and Koltun, V. (2021, January 10\u201317). Point Transformer. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref_47","unstructured":"Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., and Oh, A. (2022). Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 (NeurIPS 2022), New Orleans, LA, USA, 28 November\u20139 December 2022, Curran Associates, Inc.. Available online: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/d78ece6613953f46501b958b7bb4582f-Abstract-Conference.html."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liang, S., Zhang, L., Xie, C., and Chen, L. (2024, January 15\u201319). Causal Intervention for Panoptic Scene Graph Generation. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Niagara Falls, ON, Canada.","DOI":"10.1109\/ICME57554.2024.10687509"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4119\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T08:41:55Z","timestamp":1782808915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":48,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134119"],"URL":"https:\/\/doi.org\/10.3390\/s26134119","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}