{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:36:02Z","timestamp":1742920562553,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601219"},{"type":"electronic","value":"9789819601226"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0122-6_26","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:23:48Z","timestamp":1731781428000},"page":"297-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Object Detection Accuracy with\u00a0Hybrid Supervision and\u00a0Trans-Stage Interaction"],"prefix":"10.1007","author":[{"given":"Wenlong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Pinyan","family":"Hua","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Han, B., Guo, S.: Adamixer: a fast-converging query-based object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5364\u20135373 (2022)","key":"26_CR1","DOI":"10.1109\/CVPR52688.2022.00529"},{"doi-asserted-by":"crossref","unstructured":"Fu, S., Yan, J., Gao, Y., Xie, X., Zheng, W.-S.: ASAG: building strong one-decoder-layer sparse detectors via adaptive sparse anchor generation. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 6305\u20136315. IEEE (2023)","key":"26_CR2","DOI":"10.1109\/ICCV51070.2023.00582"},{"doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S. J.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp. 936\u2013944. IEEE Computer Society (2017)","key":"26_CR3","DOI":"10.1109\/CVPR.2017.106"},{"issue":"6","key":"26_CR4","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440-1448 (2015)","key":"26_CR5","DOI":"10.1109\/ICCV.2015.169"},{"key":"26_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7 2021. OpenReview.net (2021)","key":"26_CR7"},{"doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pp. 14454\u201314463. Computer Vision Foundation \/ IEEE (2021)","key":"26_CR8","DOI":"10.1109\/CVPR46437.2021.01422"},{"unstructured":"Yao, Z., Ai, J., Li, B., Zhang, C.: Efficient DETR: improving end-to-end object detector with dense prior. CoRR arxiv preprint arxiv: abs\/2104.01318 (2021)","key":"26_CR9"},{"doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp. 2980\u20132988. IEEE Computer Society (2017)","key":"26_CR10","DOI":"10.1109\/ICCV.2017.322"},{"doi-asserted-by":"crossref","unstructured":"Jing, W., Sun, A., Zhang, H., Li, X.: MS-DETR: Natural language video localization with sampling moment-moment interaction. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 1387\u20131400. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.77","key":"26_CR11","DOI":"10.18653\/v1\/2023.acl-long.77"},{"key":"26_CR12","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"},{"doi-asserted-by":"crossref","unstructured":"Teng, Y., Liu, H., Guo, S., Wang, L.: StageInteractor: query-based object detector with cross-stage interaction. In: IEEE\/CVF International Conference on Computer Vision (ICCV) 2023, Paris, France, October 1-6, 2023, pp. 6554\u20136565. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00605","key":"26_CR13","DOI":"10.1109\/ICCV51070.2023.00605"},{"doi-asserted-by":"crossref","unstructured":"Meng, D., et al: Conditional DETR for fast training convergence. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp. 3631\u20133640. IEEE (2021)","key":"26_CR14","DOI":"10.1109\/ICCV48922.2021.00363"},{"doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R. B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp. 5987\u20135995. IEEE Computer Society (2017)","key":"26_CR15","DOI":"10.1109\/CVPR.2017.634"},{"doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable ConvNets V2: more deformable, better results. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 9308\u20139316. Computer Vision Foundation \/ IEEE (2019)","key":"26_CR16","DOI":"10.1109\/CVPR.2019.00953"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelfth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pp. 2567\u20132575. AAAI Press (2022)","key":"26_CR17","DOI":"10.1609\/aaai.v36i3.20158"},{"unstructured":"Chen, Q., Chen, X., Zeng, G., Wang, J.: Group DETR: Fast Training Convergence with Decoupled One-to-Many Label Assignment. CoRR, arxiv preprint arxiv: abs\/2207.13085 (2022)","key":"26_CR18"},{"unstructured":"Ouyang-Zhang, J., Cho, J. H., Zhou, X., Kr\u00e4henb\u00fchl, P.: NMS Strikes Back. CoRR, arxiv preprint arxiv: abs\/2212.06137 (2022)","key":"26_CR19"},{"doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Li, J., Tang, J., Yang, J.: Generalized Focal Loss V2: learning reliable localization quality estimation for dense object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pp. 11632-11641. Computer Vision Foundation \/ IEEE (2021)","key":"26_CR20","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"26_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-030-58452-8_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Qiu","year":"2020","unstructured":"Qiu, H., Ma, Y., Li, Z., Liu, S., Sun, J.: BorderDet: border feature for dense object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 549\u2013564. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_32"},{"doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 6154\u20136162. Computer Vision Foundation \/ IEEE Computer Society (2018)","key":"26_CR22","DOI":"10.1109\/CVPR.2018.00644"},{"doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of DETR with spatially modulated co-attention. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp. 3601\u20133610. IEEE (2021)","key":"26_CR23","DOI":"10.1109\/ICCV48922.2021.00360"},{"unstructured":"Zhang, W., Cheng, T., Wang, X., Chen, S., Zhang, Q., Liu, W. Featurized Query R-CNN. CoRR, arxiv preprint arxiv: abs\/2206.06258 (2022)","key":"26_CR24"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., Luxburg, U. von, Bengio, S., Wallach, H. M., Fergus, R., Vishwanathan, S. V. N., Garnett, R. (Eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017)","key":"26_CR25"},{"doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J.Y., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 658\u2013666. Computer Vision Foundation \/ IEEE (2019)","key":"26_CR26","DOI":"10.1109\/CVPR.2019.00075"},{"doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S. E., Fu, C. Y., Berg, A. C.: SSD: Single Shot MultiBox Detector. CoRR, arxiv preprint arxiv: abs\/1512.02325 (2015)","key":"26_CR27","DOI":"10.1007\/978-3-319-46448-0_2"},{"doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 9626\u20139635. IEEE (2019)","key":"26_CR28","DOI":"10.1109\/ICCV.2019.00972"},{"doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal Loss for Dense Object Detection. CoRR, arxiv preprint arxiv: abs\/1708.02002 (2017)","key":"26_CR29","DOI":"10.1109\/ICCV.2017.324"},{"doi-asserted-by":"crossref","unstructured":"Teng, Y., Wang, L.: Structured sparse R-CNN for direct scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19437\u201319446 (2022)","key":"26_CR30","DOI":"10.1109\/CVPR52688.2022.01883"},{"doi-asserted-by":"crossref","unstructured":"Cong, Y., Liao, W., Ackermann, H., Yang, M.Y., Rosenhahn, B.: Spatial-Temporal Transformer for Dynamic Scene Graph Generation. CoRR, arxiv preprint arxiv: abs\/2107.12309 (2021)","key":"26_CR31","DOI":"10.1109\/ICCV48922.2021.01606"},{"doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You Only Look Once: Unified, Real-Time Object Detection. CoRR, arxiv preprint arxiv: abs\/1506.02640 (2015)","key":"26_CR32","DOI":"10.1109\/CVPR.2016.91"},{"unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as Points. CoRR, arxiv preprint arxiv: abs\/1904.07850 (2019)","key":"26_CR33"},{"doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 3588\u20133597. Computer Vision Foundation \/ IEEE Computer Society (2018)","key":"26_CR34","DOI":"10.1109\/CVPR.2018.00378"},{"unstructured":"Sun, Z., Cao, S., Yang, Y., Kitani, K.: Rethinking Transformer-based Set Prediction for Object Detection. CoRR, arxiv preprint arxiv: abs\/2011.10881 (2020)","key":"26_CR35"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0122-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T19:20:36Z","timestamp":1731784836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0122-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601219","9789819601226"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0122-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}