{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:20:16Z","timestamp":1766067616025,"version":"3.37.3"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019117","name":"Vector Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019117","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"longo brothers fruit markets"},{"DOI":"10.13039\/100011047","name":"AGE-WELL","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11263-022-01706-5","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T05:16:31Z","timestamp":1668143791000},"page":"407-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Robots Understanding Contextual Information in Human-Centered Environments Using Weakly Supervised Mask Data Distillation"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9563-6180","authenticated-orcid":false,"given":"Daniel","family":"Dworakowski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3669-4182","authenticated-orcid":false,"given":"Angus","family":"Fung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7080-6857","authenticated-orcid":false,"given":"Goldie","family":"Nejat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"1706_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2016). NetVLAD: CNN architecture for weakly supervised place recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5297\u20135307).","DOI":"10.1109\/CVPR.2016.572"},{"key":"1706_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., et al. (2019a). What is wrong with scene text recognition model comparisons? Dataset and model analysis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 4715\u20134723).","DOI":"10.1109\/ICCV.2019.00481"},{"key":"1706_CR3","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., & Lee, H. (2019b). Character Region Awareness for Text Detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 9365\u20139374).","DOI":"10.1109\/CVPR.2019.00959"},{"key":"1706_CR4","doi-asserted-by":"crossref","unstructured":"Barnes, D., Maddern, W., & Posner, I. (2017). Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy. In 2017 IEEE International Conference on Robotics and Automation (ICRA) (pp. 203\u2013210).","DOI":"10.1109\/ICRA.2017.7989025"},{"issue":"3","key":"1706_CR5","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/LRA.2019.2903260","volume":"4","author":"E Bellocchio","year":"2019","unstructured":"Bellocchio, E., Ciarfuglia, T. A., Costante, G., & Valigi, P. (2019). Weakly supervised fruit counting for yield estimation using spatial consistency. IEEE Robotics and Automation Letters, 4(3), 2348\u20132355.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1706_CR6","doi-asserted-by":"crossref","unstructured":"Benenson, R., Popov, S., & Ferrari, V. (2019). Large-scale interactive object segmentation with human annotators. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 11700\u201311709).","DOI":"10.1109\/CVPR.2019.01197"},{"key":"1706_CR7","doi-asserted-by":"crossref","unstructured":"Bojarski, M., Choromanska, A., Choromanski, K., Firner, B., Jackel, L., Muller, U., & Zieba, K. (2018). VisualBackProp: efficient visualization of CNNs. In 2018 IEEE International Conference on Robotics and Automation (ICRA) (pp. 4701\u20134708).","DOI":"10.1109\/ICRA.2018.8461053"},{"key":"1706_CR8","doi-asserted-by":"crossref","unstructured":"Bonechi, S., Andreini, P., Bianchini, M., & Scarselli, F. (2019). COCO_TS Dataset: Pixel\u2013level annotations based on weak supervision for scene text segmentation. In International Conference on Artificial Neural Networks and Machine Learning (pp. 238\u2013250). Cham: Springer.","DOI":"10.1007\/978-3-030-30508-6_20"},{"key":"1706_CR9","doi-asserted-by":"crossref","unstructured":"Case, C., Suresh, B., Coates, A.,& Ng, A. Y., (2011). Autonomous sign reading for semantic mapping. In 2011 IEEE international Conference on Robotics and Automation (pp. 3297\u20133303).","DOI":"10.1109\/ICRA.2011.5980523"},{"key":"1706_CR10","volume-title":"Semi-supervised learning","author":"O Chapelle","year":"2010","unstructured":"Chapelle, O., Schlkopf, B., & Zien, A. (2010). Semi-supervised learning (1st ed.). The MIT Press.","edition":"1"},{"key":"1706_CR11","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C. K., & Chan, C. S. (2017). Total-text: A comprehensive dataset for scene text detection and recognition. In 2017 14th IAPR international conference on document analysis and recognition (ICDAR) (pp. 935\u2013942).","DOI":"10.1109\/ICDAR.2017.157"},{"issue":"2","key":"1706_CR12","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1109\/TASE.2016.2631085","volume":"14","author":"J Cleveland","year":"2017","unstructured":"Cleveland, J., Thakur, D., Dames, P., Phillips, C., Kientz, T., Daniilidis, K., et al. (2017). Automated system for semantic object labeling with soft-object recognition and dynamic programming segmentation. IEEE Transactions on Automation Science and Engineering, 14(2), 820\u2013833.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"1706_CR13","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.neucom.2019.01.013","volume":"334","author":"L Deng","year":"2019","unstructured":"Deng, L., Gong, Y., Lin, Y., Shuai, J., Tu, X., Zhang, Y., et al. (2019b). Detecting multi-oriented text with corner-based region proposals. Neurocomputing, 334, 134\u2013142.","journal-title":"Neurocomputing"},{"key":"1706_CR14","doi-asserted-by":"publisher","first-page":"153400","DOI":"10.1109\/ACCESS.2019.2948405","volume":"7","author":"L Deng","year":"2019","unstructured":"Deng, L., Gong, Y., Lu, X., Lin, Y., Ma, Z., & Xie, M. (2019a). STELA: A real-time scene text detector with learned anchor. IEEE Access, 7, 153400\u2013153407.","journal-title":"IEEE Access"},{"issue":"4","key":"1706_CR15","doi-asserted-by":"publisher","first-page":"110","DOI":"10.3390\/robotics10040110","volume":"10","author":"D Dworakowski","year":"2021","unstructured":"Dworakowski, D., Thompson, C., Pham-Hung, M., & Nejat, G. (2021). A robot architecture using contextSLAM to find products in unknown crowded retail environments. Robotics, 10(4), 110.","journal-title":"Robotics"},{"issue":"1","key":"1706_CR16","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"key":"1706_CR17","unstructured":"Fu, C.-Y., Shvets, M., & Berg, A. C. (2019). RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free. arxiv."},{"issue":"2","key":"1706_CR18","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TASE.2019.2938316","volume":"17","author":"DD Gregorio","year":"2020","unstructured":"Gregorio, D. D., Tonioni, A., Palli, G., & Stefano, L. D. (2020). Semiautomatic labeling for deep learning in robotics. IEEE Transactions on Automation Science and Engineering, 17(2), 611\u2013620.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"1706_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., & Zisserman, A. (2016). Synthetic data for text localisation in natural images. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2315\u20132324).","DOI":"10.1109\/CVPR.2016.254"},{"key":"1706_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"1706_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern RecognitioN (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1706_CR22","doi-asserted-by":"crossref","unstructured":"Hou, Q., Massiceti, D., Dokania, P. K., Wei, Y., Cheng, M.-M., & Torr, P. H. (2017). Bottom-up top-down cues for weakly-supervised semantic segmentation. In International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (pp. 263\u2013277). Springer.","DOI":"10.1007\/978-3-319-78199-0_18"},{"key":"1706_CR23","unstructured":"Huang, J., Sivakumar, V., Mnatsakanyan, M., & Pang, G. (2018). Improving rotated text detection with rotation region proposal networks. arxiv."},{"key":"1706_CR24","unstructured":"Ibrahim, M. S., Vahdat, A., & Macready, W. G. (2018). Weakly supervised semantic image segmentation with self-correcting networks. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 12715\u201312725)."},{"key":"1706_CR25","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Synthetic data and artificial neural networks for natural scene text recognition. arxiv."},{"key":"1706_CR26","doi-asserted-by":"crossref","unstructured":"Jain, S. D., & Grauman, K. (2013). Predicting sufficient annotation strength for interactive foreground segmentation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1313\u20131320).","DOI":"10.1109\/ICCV.2013.166"},{"key":"1706_CR27","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1109\/TIP.2019.2926748","volume":"29","author":"L Jing","year":"2020","unstructured":"Jing, L., Chen, Y., & Tian, Y. (2020). Coarse-to-fine semantic segmentation from image-level labels. IEEE Transactions on Image Processing, 29, 225\u2013236.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1706_CR28","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., et al. (2015). ICDAR 2015 competition on robust reading. In 13th International Conference on Document Analysis and Recognition (pp. 1156\u20131160).","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"1706_CR29","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Bigorda, L. G. i, Mestre, S. R., et al. (2013). ICDAR 2013 robust reading competition. In 12th International Conference on Document Analysis and Recognition (pp. 1484\u20131493).","DOI":"10.1109\/ICDAR.2013.221"},{"key":"1706_CR30","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., & Schiele, B. (2017). Simple does it: weakly supervised instance and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 876\u2013885).","DOI":"10.1109\/CVPR.2017.181"},{"key":"1706_CR31","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., & Lampert, C. H. (2016). Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In Computer Vision\u2014ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part IV (pp. 695\u2013711).","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"1706_CR32","first-page":"25","volume":"30","author":"S Kotsiantis","year":"2005","unstructured":"Kotsiantis, S., Kanellopoulos, D., & Pintelas, P. (2005). Handling imbalanced datasets: A review. GESTS International Transactions on Computer Science and Engineering, 30, 25\u201336.","journal-title":"GESTS International Transactions on Computer Science and Engineering"},{"key":"1706_CR33","doi-asserted-by":"crossref","unstructured":"Li, G., Xie, Y., & Lin, L. (2018). Weakly supervised salient object detection using image labels. In AAAI Conf. on Artificial Intelligence (pp. 7024\u20137031).","DOI":"10.1609\/aaai.v32i1.12308"},{"key":"1706_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, T., Kang, B., Tang, S., Wang, C., Li, J., & Feng, J. (2020). Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 10991\u201311000).","DOI":"10.1109\/CVPR42600.2020.01100"},{"issue":"4","key":"1706_CR35","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1109\/TASE.2019.2900980","volume":"16","author":"H Liang","year":"2019","unstructured":"Liang, H., Sanket, N. J., Ferm\u00fcller, C., & Aloimonos, Y. (2019). SalientDSO: Bringing attention to direct sparse odometry. IEEE Transactions on Automation Science and Engineering, 16(4), 1619\u20131626.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"8","key":"1706_CR36","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao, M., Shi, B., & Bai, X. (2018a). Textboxes++: A Single-Shot Oriented Scene Text Detector. IEEE Transactions on Image Processing, 27(8), 3676\u20133690.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1706_CR37","unstructured":"Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., et al. (2018b). Scene text recognition from two-dimensional perspective, arXiv."},{"key":"1706_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P., et al. (2017). Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.324"},{"key":"1706_CR39","unstructured":"Liu, J., Liu, X., Sheng, J., Liang, D., Li, X., & Liu, Q. (2019). Pyramid mask text detector."},{"key":"1706_CR40","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., & Yan, J. (2018). FOTS fast oriented text spotting with a unified network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5676\u20135685).","DOI":"10.1109\/CVPR.2018.00595"},{"key":"1706_CR41","doi-asserted-by":"crossref","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., & Bai, X. (2018a). Mask TextSpotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. In Proceedings of the European Conference on Computer Vision (ECCV).","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"1706_CR42","doi-asserted-by":"crossref","unstructured":"Lyu, P., Yao, C., Wu, W., Yan, S., & Bai, X. (2018b). Multi-oriented scene text detection via corner localization and region segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 7553\u20137563)","DOI":"10.1109\/CVPR.2018.00788"},{"key":"1706_CR43","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-319-46466-4_8","volume-title":"Computer vision\u2014ECCV 2016","author":"A Mahendran","year":"2016","unstructured":"Mahendran, A., & Vedaldi, A. (2016). Salient deconvolutional networks. Computer vision\u2014ECCV 2016 (pp. 120\u2013135). Springer."},{"key":"1706_CR44","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., & Jawahar, C. V. (2012). Scene text recognition using higher order language priors. In British Machine Vision Conference (p. 127.1\u2013127.11).","DOI":"10.5244\/C.26.127"},{"key":"1706_CR45","doi-asserted-by":"crossref","unstructured":"Nayef, N., Yin, F., Bizid, I., Choi, H., Feng, Y., Karatzas, D., et al. (2017). ICDAR2017 Robust reading challenge on multi-lingual scene text detection and script identification\u2014RRC-MLT. In 2017 14th IAPR International Conference on Document Analysis and Recognition (pp. 1454\u20131459).","DOI":"10.1109\/ICDAR.2017.237"},{"key":"1706_CR46","doi-asserted-by":"crossref","unstructured":"Niu, S., Lin, H., Niu, T., Li, B., & Wang, X. (2019). DefectGAN: Weakly-supervised defect detection using generative adversarial network. In IEEE International Conference on Automation Science and Engineering (pp. 127\u2013132).","DOI":"10.1109\/COASE.2019.8843204"},{"issue":"1","key":"1706_CR47","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62\u201366.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"1706_CR48","unstructured":"Overview\u2014Focused Scene Text - Robust Reading Competition. (n.d.). Robust Reading Competition. https:\/\/rrc.cvc.uab.es\/?ch=2. Accessed 20 November 2020"},{"key":"1706_CR49","unstructured":"Overview\u2014ICDAR2017 Competition on Multi-lingual scene text detection and script identification - Robust Reading Competition. (2017, January 4). Robust Reading Competition. https:\/\/rrc.cvc.uab.es\/?ch=8. Accessed 20 November 2020"},{"key":"1706_CR50","unstructured":"Overview\u2014Incidental scene text - robust reading competition. (n.d.). Robust Reading Competition. https:\/\/rrc.cvc.uab.es\/?ch=4. Accessed 20 November 2020"},{"issue":"1","key":"1706_CR51","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1109\/TASE.2017.2761793","volume":"15","author":"Z Peng","year":"2018","unstructured":"Peng, Z., Gao, S., Xiao, B., Guo, S., & Yang, Y. (2018). CrowdGIS: Updating digital maps via mobile crowdsensing. IEEE Transactions on Automation Science and Engineering, 15(1), 369\u2013380.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"1706_CR52","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2017","unstructured":"Pont-Tuset, J., Arbel\u00e1ez, P., Barron, J. T., Marques, F., & Malik, J. (2017). Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 128\u2013140.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1706_CR53","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Doll\u00e1r, P., Girshick, R., Gkioxari, G., & He, K. (2018). Data distillation: Towards omni-supervised learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 4119\u20134128).","DOI":"10.1109\/CVPR.2018.00433"},{"issue":"6","key":"1706_CR54","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"1706_CR55","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., & Blake, A. (2004). \u201cGrabCut\u201d: Interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics, 23(3), 309\u2013314.","journal-title":"ACM Transactions on Graphics"},{"key":"1706_CR56","unstructured":"Ruder, S. (2017). An overview of multi-task learning in deep neural networks. arxiv."},{"key":"1706_CR57","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1109\/TPAMI.2017.2713785","volume":"40","author":"FS Saleh","year":"2018","unstructured":"Saleh, F. S., Aliakbarian, M. S., Salzmann, M., Petersson, L., Alvarez, J. M., & Gould, S. (2018). Incorporating network built-in priors in weakly-supervised semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 1382\u20131396.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"1706_CR58","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020). Grad-CAM: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128(2), 336\u2013359.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"1706_CR59","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1109\/LRA.2020.2967307","volume":"5","author":"A Shariati","year":"2020","unstructured":"Shariati, A., Holz, C., & Sinha, S. (2020). Towards privacy-preserving ego-motion estimation using an extremely low-resolution camera. IEEE Robotics and Automation Letters, 5(2), 1222\u20131229.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"11","key":"1706_CR60","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., & Yao, C. (2016). An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2298\u20132304.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1706_CR61","unstructured":"Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Deep inside convolutional networks: Visualising image classification models and saliency maps. In Workshop at International Conference on Learning Representations."},{"key":"1706_CR62","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arxiv."},{"key":"1706_CR63","doi-asserted-by":"crossref","unstructured":"Singh, A., Yang, L., & Levine, S. (2017). GPLAC: Generalizing vision-based robotic skills using weakly labeled images. In Proceedings of the IEEE International Conference on Computer Vision (pp. 5851\u20135860).","DOI":"10.1109\/ICCV.2017.623"},{"key":"1706_CR64","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., et al. (2019). Scalability in perception for autonomous driving: waymo open dataset. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 2446\u20132454).","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"1706_CR65","unstructured":"Thompson, C., Khan, H., Dworakowski, D., Harrigan, K., & Nejat, G. (2018). An autonomous shopping assistance robot for grocery stores. In IEEE\/RSJ Proceedings of the Workshop on Robotic Co-workers 4.0."},{"key":"1706_CR66","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-030-01364-6_19","volume-title":"Intravascular imaging and computer assisted stenting and large-scale annotation of biomedical data and expert label synthesis","author":"A Vardazaryan","year":"2018","unstructured":"Vardazaryan, A., Mutter, D., Marescaux, J., & Padoy, N., et al. (2018). Weakly-supervised learning for tool localization in laparoscopic videos. In D. Stoyanov, Z. Taylor, S. Balocco, R. Sznitman, A. Martel, & L. Maier-Hein (Eds.), Intravascular imaging and computer assisted stenting and large-scale annotation of biomedical data and expert label synthesis (pp. 169\u2013179). Springer."},{"issue":"6","key":"1706_CR67","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1002\/hfm.20503","volume":"24","author":"E Vilar","year":"2014","unstructured":"Vilar, E., Rebelo, F., & Noriega, P. (2014). Indoor human wayfinding performance using vertical and horizontal signage in virtual reality. Human Factors and Ergonomics in Manufacturing & Service Industries, 24(6), 601\u2013615.","journal-title":"Human Factors and Ergonomics in Manufacturing & Service Industries"},{"key":"1706_CR68","doi-asserted-by":"crossref","unstructured":"Wan, F., Liu, C., Ke, W., Ji, X., Jiao, J., & Ye, Q. (2019). C-MIL: Continuation multiple instance learning for weakly supervised object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2019.00230"},{"key":"1706_CR69","doi-asserted-by":"crossref","unstructured":"Wan, F., Wei, P., Jiao, J., Han, Z., & Ye, Q. (2018). Min-entropy latent model for weakly supervised object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00141"},{"issue":"3","key":"1706_CR70","doi-asserted-by":"publisher","first-page":"2902","DOI":"10.1109\/LRA.2019.2922582","volume":"4","author":"BH Wang","year":"2019","unstructured":"Wang, B. H., Chao, W., Wang, Y., Hariharan, B., Weinberger, K. Q., & Campbell, M. (2019). LDLS: 3-D object segmentation through label diffusion from 2-D images. IEEE Robotics and Automation Letters, 4(3), 2902\u20132909.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1706_CR71","doi-asserted-by":"publisher","first-page":"8212","DOI":"10.1109\/TIP.2021.3113157","volume":"30","author":"C Wang","year":"2021","unstructured":"Wang, C., Zhao, S., Zhu, L., Luo, K., Guo, Y., Wang, J., & Liu, S. (2021). Semi-supervised pixel-level scene text segmentation by mutually guided network. IEEE Transactions on Image Processing, 30, 8212\u20138221.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1706_CR72","doi-asserted-by":"crossref","unstructured":"Wang, H., Finn, C., Paull, L., Kaess, M., Rosenholtz, R., Teller, S., & Leonard, J. (2015). Bridging text spotting and SLAM with junction features. In 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 3701\u20133708).","DOI":"10.1109\/IROS.2015.7353895"},{"key":"1706_CR73","doi-asserted-by":"crossref","unstructured":"Wang, L., Lu, H., Wang, Y., Feng, M., Wang, D., Yin, B., & Ruan, X. (2017). Learning to detect salient objects with image-level supervision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 136\u2013145).","DOI":"10.1109\/CVPR.2017.404"},{"key":"1706_CR74","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.-M., Zhao, Y., & Yan, S. (2017). Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1568\u20131576).","DOI":"10.1109\/CVPR.2017.687"},{"key":"1706_CR75","doi-asserted-by":"crossref","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., & Huang, T. S. (2018). Revisiting dilated convolution: A simple approach for weakly- and semi-supervised semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7268\u20137277).","DOI":"10.1109\/CVPR.2018.00759"},{"key":"1706_CR76","unstructured":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis. (2020). https:\/\/github.com\/clovaai\/deep-text-recognition-benchmark. Accessed 6 June 2020"},{"issue":"2","key":"1706_CR77","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1109\/LRA.2019.2895390","volume":"4","author":"L Wellhausen","year":"2019","unstructured":"Wellhausen, L., Dosovitskiy, A., Ranftl, R., Walas, K., Cadena, C., & Hutter, M. (2019). Where should i walk? Predicting terrain properties from images via self-supervised learning. IEEE Robotics and Automation Letters, 4(2), 1509\u20131516.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1706_CR78","unstructured":"Wu, W., Xie, E., Zhang, R., Wang, W., Pang, G., Li, Z., et al. (2020). SelfText beyond polygon: Unconstrained text detection with box supervision and dynamic self-training, arXiv."},{"key":"1706_CR79","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K., test, & tst. (2017). Aggregated Residual Transformations for Deep Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1492\u20131500).","DOI":"10.1109\/CVPR.2017.634"},{"key":"1706_CR80","doi-asserted-by":"crossref","unstructured":"Zamir, A. R., Sax, A., Shen, W., Guibas, L. J., Malik, J., & Savarese, S. (2018). Taskonomy: Disentangling task transfer learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3712\u20133722).","DOI":"10.1109\/CVPR.2018.00391"},{"key":"1706_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiao, J., Wei, Y., Sun, M., & Huang, K. (2019). Reliability does matter: An End-to-end weakly supervised semantic segmentation approach. arxiv.","DOI":"10.1609\/aaai.v34i07.6971"},{"issue":"10","key":"1706_CR82","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1007\/s11263-017-1059-x","volume":"126","author":"J Zhang","year":"2018","unstructured":"Zhang, J., Bargal, S. A., Lin, Z., Brandt, J., Shen, X., & Sclaroff, S. (2018). Top-down neural attention by excitation backprop. International Journal of Computer Vision, 126(10), 1084\u20131102.","journal-title":"International Journal of Computer Vision"},{"key":"1706_CR83","doi-asserted-by":"crossref","unstructured":"Zhao, X., Liang, S., & Wei, Y. (2018). Pseudo mask augmented object detection. In Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition (pp. 4061\u20134070).","DOI":"10.1109\/CVPR.2018.00427"},{"issue":"3","key":"1706_CR84","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. International Journal of Computer Vision, 127(3), 302\u2013321.","journal-title":"International Journal of Computer Vision"},{"key":"1706_CR85","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhu, Y., Ye, Q., Qiu, Q., & Jiao, J. (2018). Weakly supervised instance segmentation using class peak response. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3791\u20133800).","DOI":"10.1109\/CVPR.2018.00399"},{"issue":"1","key":"1706_CR86","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1093\/nsr\/nwx106","volume":"5","author":"Z-H Zhou","year":"2017","unstructured":"Zhou, Z.-H. (2017). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44\u201353.","journal-title":"National Science Review"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01706-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01706-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01706-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T04:30:07Z","timestamp":1673497807000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01706-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,11]]},"references-count":86,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["1706"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01706-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2022,11,11]]},"assertion":[{"value":"23 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We have no known conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}