{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:10:31Z","timestamp":1750824631272,"version":"3.41.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319609157"},{"type":"electronic","value":"9783319609164"}],"license":[{"start":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T00:00:00Z","timestamp":1500940800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-60916-4_1","type":"book-chapter","created":{"date-parts":[[2017,7,24]],"date-time":"2017-07-24T07:53:33Z","timestamp":1500882813000},"page":"5-20","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the Robot Perception Gap with Mid-Level Vision"],"prefix":"10.1007","author":[{"given":"Chi","family":"Li","sequence":"first","affiliation":[]},{"given":"Jonathan","family":"Bohren","sequence":"additional","affiliation":[]},{"given":"Gregory D.","family":"Hager","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,7,25]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view rgb-d object dataset. In: ICRA (2011)","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Singh, A., Sha, J., Narayan, K.S., Achim, T., Abbeel, P.: BigBIRD: a large-scale 3D database of object instances. In: ICRA (2014)","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Macias, N., Wen, J.: Vision guided robotic block stacking. In: IROS (2014)","DOI":"10.1109\/IROS.2014.6942647"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Niekum, S., Osentoski, S., Konidaris, G., Chitta, S., Marthi, B., Barto, A.G.: Learning grounded finite-state representations from unstructured demonstrations. In: IJRR (2014)","DOI":"10.1177\/0278364914554471"},{"issue":"3","key":"1_CR5","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s10514-012-9305-0","volume":"33","author":"Q Lindsey","year":"2012","unstructured":"Lindsey, Q., Mellinger, D., Kumar, V.: Construction with quadrotor teams. Auton. Robot. 33(3), 323\u2013336 (2012)","journal-title":"Auton. Robot."},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Bohren, J., Papazov, C., Burschka, D., Krieger, K., Parusel, S., Haddadin, S., Shepherdson, W.L., Hager, G.D., Whitcomb, L.L.: A pilot study in vision-based augmented telemanipulation for remote assembly over high-latency networks. In: ICRA (2013)","DOI":"10.1109\/ICRA.2013.6631087"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Pauwels, K., Ivan, V., Ros, E., Vijayakumar, S.: Real-time object pose recognition and tracking with an imprecisely calibrated moving RGB-D camera. In: IROS (2014)","DOI":"10.1109\/IROS.2014.6942936"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: efficient and robust 3D object recognition. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Papazov, C., Burschka, D.: An efficient RANSAC for 3D object recognition in noisy and occluded scenes. In: ACCV (2010)","DOI":"10.1007\/978-3-642-19315-6_11"},{"key":"1_CR10","unstructured":"Hinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., Navab, N.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: ACCV, 2012 (2013)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Hager, G.D., Wegbreit, B.: Scene parsing using a prior world model. In: IJRR (2011)","DOI":"10.1177\/0278364911399340"},{"key":"1_CR12","unstructured":"Li, C., Reiter, A., Hager, G.D.: Beyond spatial pooling, fine-grained representation learning in multiple domains. In: CVPR (2015)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Knopp, J., Prasad, M., Willems, G., Timofte, R., Van Gool, L.: Hough transform and 3D SURF for robust three dimensional classification. In: ECCV (2010)","DOI":"10.1007\/978-3-642-15567-3_43"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Aldoma, A., Tombari, F., Prankl, J., Richtsfeld, A., Di Stefano, L., Vincze, M.: Multimodal cue integration through Hypotheses Verification for RGB-D object recognition and 6DOF pose estimation. In: ICRA (2013)","DOI":"10.1109\/ICRA.2013.6630859"},{"key":"1_CR15","unstructured":"Xie, Z., Singh, A., Uang, J., Narayan, K.S., Abbeel, P.: Multimodal blending for high-accuracy instance recognition. In: IROS (2013)"},{"key":"1_CR16","unstructured":"Tang, J., Miller, S., Singh, A., Abbeel, P.: A textured object recognition pipeline for color and depth image data. In: ICRA (2012)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Fischer, J., Bormann, R., Arbeiter, G., Verl, A.: A feature descriptor for texture-less object representation using 2D and 3D cues from RGB-D data. In: ICRA (2013)","DOI":"10.1109\/ICRA.2013.6630860"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. In: IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Tombari, F., Salti, S., Di Stefano, L.: A combined texture-shape descriptor for enhanced 3D feature matching. In: ICIP (2011)","DOI":"10.1109\/ICIP.2011.6116679"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Woodford, O.J., Pham, M.T., Maki, A., Perbet, F., Stenger, B.: Demisting the hough transform for 3D shape recognition and registration. In: IJCV (2014)","DOI":"10.1007\/s11263-013-0623-2"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Aldoma, A., Tombari, F., Stefano, L.D., Vincze, M.: A global hypotheses verification method for 3D object recognition. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33712-3_37"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Rusu, R.B., Bradski, G., Thibaux, R., Hsu, J.: Fast 3d recognition and pose using the viewpoint feature histogram. In: IROS (2010)","DOI":"10.1109\/IROS.2010.5651280"},{"key":"1_CR23","first-page":"2012","volume":"I","author":"S Hinterstoisser","year":"2012","unstructured":"Hinterstoisser, S., Cagniart, C., Ilic, S., Sturm, P., Navab, N., Fua, P., Lepetit, V.: Gradient response maps for real-time detection of textureless objects. PAMI I, 2012 (2012)","journal-title":"PAMI"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Richtsfeld, A., Morwald, T., Prankl, J., Zillich, M., Vincze, M: Segmentation of unknown objects in indoor environments. In: IROS (2012)","DOI":"10.1109\/IROS.2012.6385661"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Uckermann, A., Haschke, R., Ritter, H.: Realtime 3D segmentation for human-robot interaction. In: IROS (2013)","DOI":"10.1109\/IROS.2013.6696655"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Bo, L., Ren, X., Fox, D.: Unsupervised feature learning for RGB-D based object recognition. In: ISER (2013)","DOI":"10.1007\/978-3-319-00065-7_27"},{"key":"1_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"1_CR28","unstructured":"Socher, R., Huval, B., Bhat, B., Manning, C.D., Ng, A.Y.: Convolutional-recursive deep learning for 3D object classification. In: NIPS (2012)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, S., Girshick, R., Arbelez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1_CR31","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)"},{"key":"1_CR32","unstructured":"Viola, P., Jones, M.: Robust real-time object detection. In: IJCV (2001)"}],"container-title":["Springer Proceedings in Advanced Robotics","Robotics Research"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-60916-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T17:32:14Z","timestamp":1750786334000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-60916-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,25]]},"ISBN":["9783319609157","9783319609164"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-60916-4_1","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"type":"print","value":"2511-1256"},{"type":"electronic","value":"2511-1264"}],"subject":[],"published":{"date-parts":[[2017,7,25]]}}}