{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:15:27Z","timestamp":1784301327468,"version":"3.55.0"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58565-5_13","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"202-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":251,"title":["ScanRefer: 3D Object Localization in RGB-D Scans Using Natural Language"],"prefix":"10.1007","author":[{"given":"Dave Zhenyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angel X.","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"13_CR1","unstructured":"Acharya, M., Jariwala, K., Kanan, C.: VQD: visual query detection in natural scenes. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2019)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Fan, J., Hawkins, R.X., Goodman, N.D., Guibas, L.J.: ShapeGlot: learning language for shape differentiation. In: Proceedings of the International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00903"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: Proceedings of the International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"13_CR4","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Jia, S., Lo, Y.C., Chen, H.T., Liu, T.L.: See-through-text grouping for referring image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7454\u20137463 (2019)","DOI":"10.1109\/ICCV.2019.00755"},{"key":"13_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"K Chen","year":"2019","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 100\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7"},{"key":"13_CR7","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"13_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1007\/978-3-030-01249-6_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Dai","year":"2018","unstructured":"Dai, A., Nie\u00dfner, M.: 3DMV: joint 3D-multi-view prediction for 3D semantic scene segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 458\u2013474. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_28"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Datta, S., Sikka, K., Roy, A., Ahuja, K., Parikh, D., Divakaran, A.: Align2Ground: weakly supervised phrase grounding guided by image-caption alignment. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00269"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Dogan, P., Sigal, L., Gross, M.: Neural sequential phrase grounding (SeqGROUND). In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4175\u20134184 (2019)","DOI":"10.1109\/CVPR.2019.00430"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Elich, C., Engelmann, F., Schult, J., Kontogianni, T., Leibe, B.: 3D-BEVIS: birds-eye-view instance segmentation. arXiv preprint arXiv:1904.02199 (2019)","DOI":"10.1007\/978-3-030-33676-9_4"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Kontogianni, T., Leibe, B.: Dilated point convolutions: on the receptive field of point convolutions. arXiv preprint arXiv:1907.12046 (2019)","DOI":"10.1109\/ICRA40945.2020.9197503"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Feng, F., Wang, X., Li, R.: Cross-modal retrieval with correspondence autoencoder. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 7\u201316. ACM (2014)","DOI":"10.1145\/2647868.2654902"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Joty, S.R., Niu, L., Wang, G.: Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7181\u20137189 (2018)","DOI":"10.1109\/CVPR.2018.00750"},{"key":"13_CR16","unstructured":"Hong, R., Liu, D., Mo, X., He, X., Zhang, H.: Learning to compose and reason with language tree structures for visual grounding. IEEE Trans. Pattern Anal. Mach. Intell. (2019)"},{"key":"13_CR17","unstructured":"Honnibal, M., Montani, I.: spaCy 2: natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing (2017, to appear)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Hou, J., Dai, A., Nie\u00dfner, M.: 3D-SIC: 3D semantic instance completion for RGB-D scans. arXiv preprint arXiv:1904.12012 (2019)","DOI":"10.1109\/CVPR.2019.00455"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Hou, J., Dai, A., Nie\u00dfner, M.: 3D-SIS: 3D semantic instance segmentation of RGB-D scans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4421\u20134430 (2019)","DOI":"10.1109\/CVPR.2019.00455"},{"key":"13_CR20","unstructured":"Hough, P.V.: Machine analysis of bubble chamber pictures. In: Conference Proceedings, vol. 590914, pp. 554\u2013558 (1959)"},{"key":"13_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4555\u20134564 (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Wang, L.: Instance-aware image and sentence matching with selective multimodal LSTM. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2310\u20132318 (2017)","DOI":"10.1109\/CVPR.2017.767"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., Wang, L.: Learning semantic concepts and order for image and sentence matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6163\u20136171 (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"13_CR26","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.: Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in Neural Information Processing Systems, pp. 1889\u20131897 (2014)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"13_CR28","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR29","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Kong, C., Lin, D., Bansal, M., Urtasun, R., Fidler, S.: What are you talking about? Text-to-image coreference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133565 (2014)","DOI":"10.1109\/CVPR.2014.455"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Lahoud, J., Ghanem, B., Pollefeys, M., Oswald, M.R.: 3D instance segmentation via multi-task metric learning. arXiv preprint arXiv:1906.08650 (2019)","DOI":"10.1109\/ICCV.2019.00935"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Referring image segmentation via recurrent refinement networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Yang, W., Wang, X.: Identity-aware textual-visual matching with latent co-attention. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1890\u20131899 (2017)","DOI":"10.1109\/ICCV.2017.209"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1271\u20131280 (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Liu, D., Zhang, H., Wu, F., Zha, Z.J.: Learning to assemble neural module tree networks for visual grounding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4673\u20134682 (2019)","DOI":"10.1109\/ICCV.2019.00477"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Liu, X., Wang, Z., Shao, J., Wang, X., Li, H.: Improving referring expression grounding with cross-modal attention-guided erasing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1950\u20131959 (2019)","DOI":"10.1109\/CVPR.2019.00205"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"13_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1007\/978-3-030-01252-6_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"E Margffoy-Tuay","year":"2018","unstructured":"Margffoy-Tuay, E., P\u00e9rez, J.C., Botero, E., Arbel\u00e1ez, P.: Dynamic multimodal instance segmentation guided by natural language queries. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 656\u2013672. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_39"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Mauceri, C., Palmer, M., Heckman, C.: SUN-Spot: an RGB-D dataset with spatial referring expressions. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00236"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Narita, G., Seno, T., Ishikawa, T., Kaji, Y.: PanopticFusion: online volumetric semantic mapping at the level of stuff and things. arXiv preprint arXiv:1903.01177 (2019)","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Do, T.T., Reid, I., Caldwell, D.G., Tsagarakis, N.G.: Object captioning and retrieval with natural language. arXiv preprint arXiv:1803.06152 (2018)","DOI":"10.1109\/ICCVW.2019.00316"},{"key":"13_CR43","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"13_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-01258-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"BA Plummer","year":"2018","unstructured":"Plummer, B.A., Kordas, P., Kiapour, M.H., Zheng, S., Piramuthu, R., Lazebnik, S.: Conditional image-text embedding networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 258\u2013274. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_16"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"13_CR47","doi-asserted-by":"crossref","unstructured":"Prabhudesai, M., Tung, H.Y.F., Javed, S.A., Sieb, M., Harley, A.W., Fragkiadaki, K.: Embodied language grounding with implicit 3D visual feature representations. arXiv preprint arXiv:1910.01210 (2019)","DOI":"10.1109\/CVPR42600.2020.00229"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"13_CR49","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"13_CR50","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, pp. 5099\u20135108 (2017)"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Qi, Y., Wu, Q., Anderson, P., Liu, M., Shen, C., van den Hengel, A.: REVERIE: remote embodied visual referring expression in real indoor environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"13_CR52","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396 (2016)"},{"key":"13_CR53","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, pp. 91\u201399 (2015)"},{"key":"13_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Zero-shot grounding of objects from natural language queries. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4694\u20134703 (2019)","DOI":"10.1109\/ICCV.2019.00479"},{"key":"13_CR56","unstructured":"Sharma, S., Suhubdy, D., Michalski, V., Kahou, S.E., Bengio, Y.: ChatPainter: improving text to image generation using dialogue. arXiv preprint arXiv:1802.08216 (2018)"},{"key":"13_CR57","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"13_CR58","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"2","key":"13_CR59","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 394\u2013407 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR60","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"13_CR61","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Cao, J., Shen, C., Gao, L., van den Hengel, A.: Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1960\u20131968 (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Xiao, F., Sigal, L., Jae Lee, Y.: Weakly-supervised visual grounding of phrases with linguistic structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5945\u20135954 (2017)","DOI":"10.1109\/CVPR.2017.558"},{"key":"13_CR63","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"13_CR64","unstructured":"Yang, B., et al.: Learning object bounding boxes for 3D instance segmentation on point clouds. arXiv preprint arXiv:1906.01140 (2019)"},{"key":"13_CR65","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4145\u20134154 (2019)","DOI":"10.1109\/CVPR.2019.00427"},{"key":"13_CR66","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4644\u20134653 (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"13_CR67","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4683\u20134693 (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"13_CR68","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10502\u201310511 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"13_CR69","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"13_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"13_CR71","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7282\u20137290 (2017)","DOI":"10.1109\/CVPR.2017.375"},{"key":"13_CR72","doi-asserted-by":"crossref","unstructured":"Zhao, F., Li, J., Zhao, J., Feng, J.: Weakly supervised phrase localization with multi-scale anchored transformer network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5696\u20135705 (2018)","DOI":"10.1109\/CVPR.2018.00597"},{"key":"13_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58565-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:05:19Z","timestamp":1731283519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}