{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:38Z","timestamp":1740123578635,"version":"3.37.3"},"reference-count":101,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Science Foundation","award":["CAREER 149783"],"award-info":[{"award-number":["CAREER 149783"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1007\/s11263-019-01212-1","type":"journal-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T13:10:31Z","timestamp":1567516231000},"page":"96-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Tracking Persons-of-Interest via Unsupervised Representation Adaptation"],"prefix":"10.1007","volume":"128","author":[{"given":"Shun","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jia-Bin","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jongwoo","family":"Lim","sequence":"additional","affiliation":[]},{"given":"Yihong","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Jinjun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Narendra","family":"Ahuja","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,3]]},"reference":[{"key":"1212_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., & Schiele, B. (2008). People-tracking-by-detection and people-detection-by-tracking. In CVPR.","DOI":"10.1109\/CVPR.2008.4587583"},{"key":"1212_CR2","doi-asserted-by":"crossref","unstructured":"Andriyenko, A., & Schindler, K. (2011). Multi-target tracking by continuous energy minimization. In CVPR.","DOI":"10.1109\/CVPR.2011.5995311"},{"key":"1212_CR3","doi-asserted-by":"crossref","unstructured":"Andriyenko, A., Schindler, K., & Roth, S. (2012). Discrete-continuous optimization for multi-target tracking. In CVPR.","DOI":"10.1109\/CVPR.2012.6247893"},{"key":"1212_CR4","doi-asserted-by":"crossref","unstructured":"Anguelov, D., Lee, K. C., Gokturk, S. B., & Sumengen, B. (2007). Contextual identity recognition in personal photo albums. In CVPR.","DOI":"10.1109\/CVPR.2007.383057"},{"key":"1212_CR5","doi-asserted-by":"crossref","unstructured":"Ayazoglu, M., Sznaier, M., & Camps, O. I. (2012) Fast algorithms for structured robust principal component analysis. In CVPR.","DOI":"10.1109\/CVPR.2012.6247865"},{"key":"1212_CR6","doi-asserted-by":"crossref","unstructured":"Bauml, M., Tapaswi, M., & Stiefelhagen, R. (2013). Semi-supervised learning with constraints for person identification in multimedia data. In CVPR.","DOI":"10.1109\/CVPR.2013.462"},{"key":"1212_CR7","doi-asserted-by":"crossref","unstructured":"Ben\u00a0Shitrit, H., Berclaz, J., Fleuret, F., & Fua, P. (2011). Tracking multiple people under global appearance constraints. In ICCV.","DOI":"10.1109\/ICCV.2011.6126235"},{"issue":"9","key":"1212_CR8","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","volume":"33","author":"J Berclaz","year":"2011","unstructured":"Berclaz, J., Fleuret, F., Turetken, E., & Fua, P. (2011). Multiple object tracking using k-shortest paths optimization. PAMI, 33(9), 1806\u20131819.","journal-title":"PAMI"},{"key":"1212_CR9","unstructured":"Bertinetto, L., Henriques, J. F., Valmadre, J., Torr, P., & Vedaldi, A. (2016) Learning feed-forward one-shot learners. In NIPS (pp. 523\u2013531)."},{"key":"1212_CR10","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., & Torr, P. H. (2016). Fully-convolutional siamese networks for object tracking. In European conference on computer vision (pp. 850\u2013865). Springer.","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"1212_CR11","doi-asserted-by":"crossref","unstructured":"Bourdev, L., & Malik, J. (2009). Poselets: Body part detectors trained using 3d human pose annotations. In ICCV (pp. 1365\u20131372).","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"1212_CR12","doi-asserted-by":"crossref","unstructured":"Breitenstein, M. D., Reichlin, F., Leibe, B., Koller-Meier, E., & Van\u00a0Gool, L. (2009). Robust tracking-by-detection using a detector confidence particle filter. In ICCV.","DOI":"10.1109\/ICCV.2009.5459278"},{"key":"1212_CR13","doi-asserted-by":"crossref","unstructured":"Brendel, W., Amer, M., & Todorovic, S. (2011). Multiobject tracking as maximum weight independent set. In CVPR.","DOI":"10.1109\/CVPR.2011.5995395"},{"key":"1212_CR14","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K. K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., & Van Gool, L. (2017). One-shot video object segmentation. In CVPR. IEEE.","DOI":"10.1109\/CVPR.2017.565"},{"key":"1212_CR15","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018). Vggface2: A dataset for recognising faces across pose and age. In FG (pp. 67\u201374). IEEE.","DOI":"10.1109\/FG.2018.00020"},{"key":"1212_CR16","unstructured":"Chopra, S., Hadsell, R., & LeCun, Y. (2005) Learning a similarity metric discriminatively, with application to face verification. In CVPR."},{"key":"1212_CR17","doi-asserted-by":"crossref","unstructured":"Cinbis, R. G., Verbeek, J., & Schmid, C. (2011). Unsupervised metric learning for face identification in tv video. In ICCV.","DOI":"10.1109\/ICCV.2011.6126415"},{"key":"1212_CR18","doi-asserted-by":"crossref","unstructured":"Collins, R. T. (2012). Multitarget data association with higher-order motion models. In CVPR.","DOI":"10.1109\/CVPR.2012.6247870"},{"issue":"10","key":"1212_CR19","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1109\/TPAMI.2005.205","volume":"27","author":"RT Collins","year":"2005","unstructured":"Collins, R. T., Liu, Y., & Leordeanu, M. (2005). Online selection of discriminative tracking features. PAMI, 27(10), 1631\u20131643.","journal-title":"PAMI"},{"key":"1212_CR20","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR.","DOI":"10.1109\/CVPR.2005.177"},{"key":"1212_CR21","doi-asserted-by":"crossref","unstructured":"Dicle, C., Camps, O. I., Sznaier, M. (2013). The way they move: Tracking multiple targets with similar appearance. In ICCV.","DOI":"10.1109\/ICCV.2013.286"},{"key":"1212_CR22","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., et\u00a0al. (2014). Decaf: A deep convolutional activation feature for generic visual recognition. In ICML."},{"issue":"9","key":"1212_CR23","doi-asserted-by":"publisher","first-page":"1762","DOI":"10.1109\/TPAMI.2015.2497689","volume":"38","author":"M Du","year":"2016","unstructured":"Du, M., & Chellappa, R. (2016). Face association for videos using conditional random fields and max-margin markov networks. PAMI, 38(9), 1762\u20131773.","journal-title":"PAMI"},{"key":"1212_CR24","doi-asserted-by":"crossref","unstructured":"El\u00a0Khoury, E., Senac, C., & Joly, P. (2010). Face-and-clothing based people clustering in video content. In ICMR.","DOI":"10.1145\/1743384.1743435"},{"key":"1212_CR25","unstructured":"Everingham, M., Sivic, J., & Zisserman, A. (2006). \u201cHello! My name is... Buffy\u201d\u2014Automatic naming of characters in tv video. In BMVC."},{"key":"1212_CR26","doi-asserted-by":"crossref","unstructured":"Fernando, B., Habrard, A., Sebban, M., & Tuytelaars, T. (2013). Unsupervised visual domain adaptation using subspace alignment. In ICCV (pp. 2960\u20132967).","DOI":"10.1109\/ICCV.2013.368"},{"key":"1212_CR27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patrec.2015.07.009","volume":"65","author":"B Fernando","year":"2015","unstructured":"Fernando, B., Tommasi, T., & Tuytelaars, T. (2015). Joint cross-domain classification and subspace learning for unsupervised adaptation. Pattern Recognition Letters, 65, 60\u201366.","journal-title":"Pattern Recognition Letters"},{"key":"1212_CR28","doi-asserted-by":"crossref","unstructured":"Fulkerson, B., Vedaldi, A., & Soatto, S. (2008). Localizing objects with smart dictionaries. In ECCV.","DOI":"10.1007\/978-3-540-88682-2_15"},{"key":"1212_CR29","unstructured":"Ganin, Y., & Lempitsky, V. (2014) Unsupervised domain adaptation by backpropagation. arXiv."},{"issue":"1","key":"1212_CR30","first-page":"2096","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., et al. (2016). Domain-adversarial training of neural networks. The Journal of Machine Learning Research, 17(1), 2096\u20132030.","journal-title":"The Journal of Machine Learning Research"},{"key":"1212_CR31","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et\u00a0al. (2014). Generative adversarial nets. In NIPS (pp. 2672\u20132680)."},{"key":"1212_CR32","doi-asserted-by":"crossref","unstructured":"Grabner, H., & Bischof, H. (2006). On-line boosting and vision. In CVPR.","DOI":"10.1109\/CVPR.2006.215"},{"key":"1212_CR33","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., & Malik, J. (2016). Cross modal distillation for supervision transfer. In CVPR (pp. 2827\u20132836).","DOI":"10.1109\/CVPR.2016.309"},{"key":"1212_CR34","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., & LeCun, Y. (2006). Dimensionality reduction by learning an invariant mapping. In CVPR.","DOI":"10.1109\/CVPR.2006.100"},{"key":"1212_CR35","doi-asserted-by":"crossref","unstructured":"Hu, J., Lu, J., & Tan, Y. P. (2014). Discriminative deep metric learning for face verification in the wild. In CVPR.","DOI":"10.1109\/CVPR.2014.242"},{"key":"1212_CR36","unstructured":"Huang, C., Li, Y., Ai, H., et\u00a0al. (2006). Robust head tracking with particles based on multiple cues. In ECCVW."},{"key":"1212_CR37","doi-asserted-by":"crossref","unstructured":"Huang, C., Wu, B., & Nevatia, R. (2008). Robust object tracking by hierarchical association of detection responses. In ECCV.","DOI":"10.1007\/978-3-540-88688-4_58"},{"key":"1212_CR38","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R. et\u00a0al. (2014). Caffe: Convolutional architecture for fast feature embedding. In ACM MM.","DOI":"10.1145\/2647868.2654889"},{"key":"1212_CR39","doi-asserted-by":"crossref","unstructured":"Jiang, H., Fels, S., & Little, J. J. (2007). A linear programming approach for multiple object tracking. In CVPR.","DOI":"10.1109\/CVPR.2007.383180"},{"key":"1212_CR40","unstructured":"Joon\u00a0Oh, S., Benenson, R., Fritz, M., & Schiele, B. (2015). Person recognition in personal photo collections. In ICCV (pp. 3862\u20133870)."},{"issue":"7","key":"1212_CR41","first-page":"1409","volume":"34","author":"Z Kalal","year":"2012","unstructured":"Kalal, Z., Mikolajczyk, K., & Matas, J. (2012). Tracking-learning-detection. PAMI, 34(7), 1409\u20131422.","journal-title":"Tracking-learning-detection. PAMI"},{"key":"1212_CR42","doi-asserted-by":"crossref","unstructured":"Kaucic, R., Perera, A. A., Brooksby, G., Kaufhold, J., & Hoogs, A. (2005). A unified framework for tracking through occlusions and across sensor gaps. In CVPR.","DOI":"10.1109\/CVPR.2005.53"},{"key":"1212_CR43","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In NIPS."},{"key":"1212_CR44","doi-asserted-by":"crossref","unstructured":"Kuo, C. H., Huang, C., & Nevatia, R. (2010). Multi-target tracking by on-line learned discriminative appearance models. In CVPR.","DOI":"10.1109\/CVPR.2010.5540148"},{"key":"1212_CR45","doi-asserted-by":"crossref","unstructured":"Kuo, C. H., & Nevatia, R. (2011). How does person identity recognition help multi-person tracking? In CVPR.","DOI":"10.1109\/CVPR.2011.5995384"},{"key":"1212_CR46","doi-asserted-by":"crossref","unstructured":"Leibe, B., Schindler, K., & Van\u00a0Gool, L. (2007). Coupled detection and trajectory estimation for multi-object tracking. In ICCV.","DOI":"10.1109\/ICCV.2007.4408936"},{"key":"1212_CR47","doi-asserted-by":"crossref","unstructured":"Li, Y., Ai, H., Yamashita, T., Lao, S., & Kawade, M. (2007). Tracking in low frame rate video: A cascade particle filter with discriminative observers of different lifespans. In CVPR.","DOI":"10.1109\/CVPR.2007.383199"},{"key":"1212_CR48","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., & Nevatia, R. (2009). Learning to associate: Hybridboosted multi-target tracker for crowded scene. In CVPR.","DOI":"10.1109\/CVPR.2009.5206735"},{"key":"1212_CR49","doi-asserted-by":"crossref","unstructured":"Lin, D., Kapoor, A., Hua, G., & Baker, S. (2010). Joint people, event, and location recognition in personal photo collections using cross-domain context. In ECCV.","DOI":"10.1007\/978-3-642-15549-9_18"},{"key":"1212_CR50","unstructured":"Lin, Z., Courbariaux, M., Memisevic, R., & Bengio, Y. (2015). Neural networks with few multiplications. arXiv."},{"key":"1212_CR51","unstructured":"Liu, M. Y., & Tuzel, O. (2016). Coupled generative adversarial networks. In NIPS (pp. 469\u2013477)."},{"key":"1212_CR52","doi-asserted-by":"crossref","unstructured":"Long, M., Wang, J., Ding, G., Sun, J., & Yu, P. S. (2013). Transfer feature learning with joint distribution adaptation. In ICCV (pp. 2200\u20132207).","DOI":"10.1109\/ICCV.2013.274"},{"issue":"2","key":"1212_CR53","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. IJCV, 60(2), 91\u2013110.","journal-title":"IJCV"},{"key":"1212_CR54","doi-asserted-by":"crossref","unstructured":"Mathias, M., Benenson, R., Pedersoli, M., & Van\u00a0Gool, L. (2014). Face detection without bells and whistles. In ECCV.","DOI":"10.1007\/978-3-319-10593-2_47"},{"key":"1212_CR55","doi-asserted-by":"crossref","unstructured":"Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015). Deep face recognition. In BMVC.","DOI":"10.5244\/C.29.41"},{"key":"1212_CR56","doi-asserted-by":"crossref","unstructured":"Paul, G., Elie, K., Sylvain, M., Jean-Marc, O., & Paul, D. (2014). A conditional random field approach for audio-visual people diarization. In ICASSP.","DOI":"10.1109\/ICASSP.2014.6853569"},{"key":"1212_CR57","doi-asserted-by":"crossref","unstructured":"Pellegrini, S., Ess, A., Schindler, K., & Van\u00a0Gool, L. (2009). You\u2019ll never walk alone: Modeling social behavior for multi-target tracking. In ICCV.","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"1212_CR58","doi-asserted-by":"crossref","unstructured":"Perera, A. A., Srinivas, C., Hoogs, A., Brooksby, G., & Hu, W. (2006). Multi-object tracking through simultaneous long occlusions and split-merge conditions. In CVPR.","DOI":"10.1109\/CVPR.2006.195"},{"key":"1212_CR59","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-642-33885-4_61","volume-title":"Computer Vision \u2013 ECCV 2012. Workshops and Demonstrations","author":"Federico Pernici","year":"2012","unstructured":"Pernici, F. (2012). Facehugger: The alien tracker applied to faces. In ECCV."},{"key":"1212_CR60","doi-asserted-by":"crossref","unstructured":"Ramanan, D., Baker, S., & Kakade, S. (2007). Leveraging archival video for building face datasets. In ICCV.","DOI":"10.1109\/ICCV.2007.4409012"},{"key":"1212_CR61","doi-asserted-by":"crossref","unstructured":"Rao, Y., Lin, J., Lu, J., & Zhou, J. (2017). Learning discriminative aggregation network for video-based face recognition. In Proceedings of the IEEE international conference on computer vision (pp. 3781\u20133790).","DOI":"10.1109\/ICCV.2017.408"},{"issue":"6\u20137","key":"1212_CR62","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/s11263-018-1135-x","volume":"127","author":"Y Rao","year":"2019","unstructured":"Rao, Y., Lu, J., & Zhou, J. (2019). Learning discriminative aggregation network for video-based face recognition and person re-identification. International Journal of Computer Vision, 127(6\u20137), 701\u2013718.","journal-title":"International Journal of Computer Vision"},{"key":"1212_CR63","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"1212_CR64","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C. (2016). Performance measures and a data set for multi-target, multi-camera tracking. In ECCVW (pp. 17\u201335). Springer.","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"1212_CR65","unstructured":"Roth, M., Bauml, M., Nevatia, R., & Stiefelhagen, R. (2012). Robust multi-pose face tracking by multi-stage tracklet association. In ICPR."},{"key":"1212_CR66","doi-asserted-by":"crossref","unstructured":"Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010). Adapting visual category models to new domains. In ECCV (pp. 213\u2013226). Springer.","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"1212_CR67","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. In CVPR.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"1212_CR68","unstructured":"Shu, R., Bui, H. H., Narui, H., & Ermon, S. (2018). A dirt-t approach to unsupervised domain adaptation. In ICLR."},{"key":"1212_CR69","doi-asserted-by":"crossref","unstructured":"Sivic, J., Everingham, M., & Zisserman, A. (2009). \u201cWho are you?\u201d\u2014Learning person specific classifiers from video. In CVPR.","DOI":"10.1109\/CVPR.2009.5206513"},{"key":"1212_CR70","doi-asserted-by":"crossref","unstructured":"Stauffer, C. (2003). Estimating tracking sources and sinks. In CVPR.","DOI":"10.1109\/CVPRW.2003.10036"},{"key":"1212_CR71","doi-asserted-by":"crossref","unstructured":"Sun, B., Feng, J., & Saenko, K. (2016). Return of frustratingly easy domain adaptation. In AAAI (Vol.\u00a06, p.\u00a08).","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"1212_CR72","doi-asserted-by":"crossref","unstructured":"Sun, B., & Saenko, K. (2016). Deep coral: Correlation alignment for deep domain adaptation. In ECCV (pp. 443\u2013450). Springer.","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"1212_CR73","unstructured":"Sun, Y., Chen, Y., Wang, X., & Tang, X. (2014a). Deep learning face representation by joint identification-verification. In NIPS."},{"key":"1212_CR74","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., & Tang, X. (2014b). Deep learning face representation from predicting 10,000 classes. In CVPR.","DOI":"10.1109\/CVPR.2014.244"},{"key":"1212_CR75","unstructured":"Taigman, Y., Polyak, A., & Wolf, L. (2016). Unsupervised cross-domain image generation. arXiv preprint arXiv:1611.02200 ."},{"key":"1212_CR76","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. In CVPR.","DOI":"10.1109\/CVPR.2014.220"},{"key":"1212_CR77","unstructured":"Tang, Z., Zhang, Y., Li, Z., & Lu, H. (2015). Face clustering in videos with proportion prior. In IJCAI."},{"key":"1212_CR78","unstructured":"Tapaswi, M., Bauml, M., & Stiefelhagen, R. (2012). \u201cKnock! Knock! Who is it?\u201d probabilistic person identification in tv-series. In CVPR."},{"key":"1212_CR79","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Parkhi, O. M., Rahtu, E., Sommerlade, E., Stiefelhagen, R., & Zisserman, A. (2014). Total cluster: A person agnostic clustering method for broadcast videos. In ICVGIP.","DOI":"10.1145\/2683483.2683490"},{"key":"1212_CR80","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7167\u20137176).","DOI":"10.1109\/CVPR.2017.316"},{"key":"1212_CR81","unstructured":"Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014). Deep domain confusion: Maximizing for domain invariance. arXiv."},{"issue":"2579\u20132605","key":"1212_CR82","first-page":"85","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-sne. JMLR, 9(2579\u20132605), 85.","journal-title":"JMLR"},{"key":"1212_CR83","doi-asserted-by":"crossref","unstructured":"Varghese, J., & Nair, K. (2016). Detecting video shot boundaries by modified tomography. In VisionNet (pp. 131\u2013135). ACM.","DOI":"10.1145\/2983402.2983441"},{"key":"1212_CR84","doi-asserted-by":"crossref","unstructured":"Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In CVPR.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"1212_CR85","doi-asserted-by":"crossref","unstructured":"Wang, B., Wang, G., Chan, K. L., & Wang, L. (2014). Tracklet association with online target-specific metric learning. In CVPR.","DOI":"10.1109\/CVPR.2014.161"},{"key":"1212_CR86","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP) (pp. 3645\u20133649). IEEE.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"1212_CR87","doi-asserted-by":"crossref","unstructured":"Wu, B., Lyu, S., Hu, B. G., & Ji, Q. (2013a). Simultaneous clustering and tracklet linking for multi-face tracking in videos. In ICCV.","DOI":"10.1109\/ICCV.2013.355"},{"key":"1212_CR88","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhang, Y., Hu, B. G., & Ji, Q. (2013b). Constrained clustering and its application to face clustering in videos. In CVPR.","DOI":"10.1109\/CVPR.2013.450"},{"key":"1212_CR89","doi-asserted-by":"crossref","unstructured":"Xiao, S., Tan, M., & Xu, D. (2014). Weighted block-sparse low rank representation for face clustering in videos. In ECCV.","DOI":"10.1007\/978-3-319-10599-4_9"},{"key":"1212_CR90","unstructured":"Xing, J., Ai, H., & Lao, S. (2009). Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses. In CVPR."},{"key":"1212_CR91","unstructured":"Yang, B., Nevatia, R. (2012a). Multi-target tracking by online learning of non-linear motion patterns and robust appearance models. In CVPR."},{"key":"1212_CR92","doi-asserted-by":"crossref","unstructured":"Yang, B., & Nevatia, R. (2012b). Online learned discriminative part-based appearance models for multi-human tracking. In ECCV.","DOI":"10.1007\/978-3-642-33718-5_35"},{"key":"1212_CR93","unstructured":"Yi, D., Lei, Z., Liao, S., & Li, S. Z. (2014). Learning face representation from scratch. arXiv."},{"key":"1212_CR94","doi-asserted-by":"crossref","unstructured":"Yoon, J. S., Rameau, F., Kim, J., Lee, S., Shin, S., & Kweon, I. S. (2017). Pixel-level matching for video object segmentation using convolutional neural networks. In ICCV (pp. 2186\u20132195). IEEE.","DOI":"10.1109\/ICCV.2017.238"},{"key":"1212_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, L., Li, Y., & Nevatia, R. (2008). Global data association for multi-object tracking using network flows. In CVPR.","DOI":"10.1109\/CVPR.2008.4587584"},{"key":"1212_CR96","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Taigman, Y., Fergus, R., & Bourdev, L. (2015). Beyond frontal faces: Improving person recognition using multiple cues. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4804\u20134813).","DOI":"10.1109\/CVPR.2015.7299113"},{"issue":"2","key":"1212_CR97","first-page":"580","volume":"48","author":"S Zhang","year":"2015","unstructured":"Zhang, S., Wang, J., Wang, Z., Gong, Y., & Liu, Y. (2015). Multi-target tracking by learning local-to-global trajectory models. PR, 48(2), 580\u2013590.","journal-title":"PR"},{"key":"1212_CR98","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Luo, P., Loy, C. C., & Tang, X. (2016). Joint face representation adaptation and clustering in videos. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_15"},{"key":"1212_CR99","doi-asserted-by":"crossref","unstructured":"Zhao, X., Gong, D., & Medioni, G. (2012). Tracking using motion patterns for very crowded scenes. In ECCV.","DOI":"10.1007\/978-3-642-33709-3_23"},{"key":"1212_CR100","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In ICCV.","DOI":"10.1109\/ICCV.2015.133"},{"key":"1212_CR101","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, C., Fu, H., Wang, R., & Cao, X. (2015). Multi-cue augmented face clustering. In ACM MM.","DOI":"10.1145\/2733373.2806290"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01212-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01212-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01212-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T08:53:40Z","timestamp":1664268820000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01212-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,3]]},"references-count":101,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["1212"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01212-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2019,9,3]]},"assertion":[{"value":"13 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}