Search

Your search keyword '"Shotton, J."' showing total 208 results
Start Over Author "Shotton, J."
208 results on '"Shotton, J."'

15. Conclusions

Author

Criminisi, A., Shotton, J., Criminisi, A., editor, and Shotton, J., editor

Published
2013
Full Text
View/download PDF

16. Decision Forests for Tissue-Specific Segmentation of High-Grade Gliomas in Multi-channel MR

Author

Zikic, Darko, Glocker, Ben, Konukoglu, Ender, Criminisi, Antonio, Demiralp, C., Shotton, J., Thomas, O. M., Das, T., Jena, R., Price, S. J., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Ayache, Nicholas, editor, Delingette, Hervé, editor, Golland, Polina, editor, and Mori, Kensaku, editor

Published
2012
Full Text
View/download PDF

19. Association between age at disease onset of anti-neutrophil cytoplasmic antibody-associated vasculitis and clinical presentation and short-term outcomes

Author

Monti, S., Craven, A., Klersy, C., Montecucco, C., Caporali, R., Watts, R., Merkel, P. A., Luqmani, R., Achilleos, K., Adler, M., Alba, M. A., Albert, D. A., Alibaz-Oner, F., Allcoat, P., Amano, K., Amarasuriya, M., Amudala, N. A., Andrews, J., Archer, A. M., Arimura, Y., Atukorala, I., Azevedo, E., Bajad, S., Baldwin, C., Barra, L. J., Baslund, B., Basu, N., Baykal, M., Berger, C., Berglin, E., Besada, E., Bhardwaj, M., Bischof, A., Blockmans, D., Blood, J., Draibe, J. B., Brand, S., Brandao, M., Bruce, I. N., Butler, A., Calabrese, L. H., Ferrer, D. C., Carette, S., Carmona, D., Ceunen, H., Chakravarty, K., Chapman, P. T., Chocova, Z., Chung, S. A., Ci, W., Cid, M. C., Clark, T. M., Clarkson, M. R., De Jesus Contreras-Rodriguez, F., Conway, R., Cooke, K., Viros, X. C., Cordeiro, A., Costa, A., Culfear, K., Daikeler, T., Danda, D., Das, S. K., Dasgupta, B., De Castro, A. M., Dehghan, N., Devassy, R., Dhindsa, N., Diamantopoulos, A. P., Direskeneli, H., Dobashi, H., Juan, D., Durrani, M., Edelsten, C., Eifert, J., Elhayek, S., Elsideeg, S., Endo, T., Erden, A., Erer, B., Eriksson, P., Erturk, Z., Espigol-Frigole, G., Felicetti, M., Ferraro, A., Ferro, J. M., Fifi-Mah, A., Flores-Suarez, L. F., Flossmann, O., Flynn, D., Fonseca, J. E., Foot, J., Foote, M., Forbess, L., Fujimoto, S., Fukuoka, K., Furtado, C., Furuta, S., Gaffo, A. L., Gallagher, P., Gao, N., Gatenby, P., Gendi, N., Geraldes, R., Gerits, A., Gioffredi, A., Gomples, L., Goncalves, M. J., Gondo, P., Graham, A., Grainger, R., Gray, D. T., Grayson, P. C., Griffiths, L., Guo, Y., Gupta, R., Gylling, M., Hajj-Ali, R. A., Hammam, N., Harigai, M., Hartley, L., Haslett, J., Hassan, A., Hatemi, G., Hellmich, B., Henckaerts, L., Henes, J. C., Hepburn, J., Herd, V., Hess, C., Hill, C., Hinojosa-Azaola, A., Hirahashi, J., Hirano, F., Hocevar, A., Holle, J., Hollinger, N., Homma, S., Howard, T., Hoyles, R. K., Hruskova, Z., Hutcheon, G., Ignacak, M., Igney-Oertel, A., Ikeda, K., Ikegaya, N., Jagadeesh, S., Jaquith, J., Jayne, D. R. W., Jewell, T., Jones, C., Joshi, A., Kalyoncu, U., Kamall, S., Kamath, S., Lai, K. S., Kaname, S., Kanchinadham, S., Karadag, O., Karube, M., Kaszuba, M., Kaur, R., Kawakami, T., Kawashima, S., Khalidi, N., Khan, A., Kikuchi, M., Kilic, L., Kimura, M., King, M. J., Klapa, S., Klocke, R., Kobayashi, T., Kobayashi, S., Komagata, Y., Kronbichler, A., Kuczia, P., Kumar, M. S., Kurosawa, M., Lamprecht, P., Langford, C. A., Lanyon, P., Laversuch, C., Lee, S. J., Leoni, S., Li, J., Liang, K., Liang, P., Liao, H., Lee, L. A., Luqmani, R. A., Lyle, A., Macdonald, M., Mackie, S. L., Madden, L., Magliano, M., Makino, H., Makol, A., Malaiya, R., Malaviya, A., Manthri, R., Maritati, F., Da Silva, A. M., Mason, J. C., Matara, C., Matsui, K., Matteson, E. L., Mcbride, D., Mccullough, K., Mcgeoch, L., Mclaren, J., Mcmillian, C., Mendiratta, N., Menon, A., Merinopoulos, D., Merkel, P., Messier, S., Micheletti, R. G., Mills, K., Milman, N., Minoda, M., Minz, R. W., Mock, C., Mohammad, A. J., Moiseev, S., Moitinho, M., Molloy, E., Monach, P. A., Montgomery, M., Moosig, F., Moradizadeh, M., Morgan, M., Morgan, A. W., Morgan, A. -M., Muir, A., Mukhtyar, C., Muller, A., Muratore, F., Muso, E., Nada, R., Nakajima, H., Nakajima, T., Nakano, H., Nandagudi, A., Neumann, T., Y. F., Ng, K. H., Ng, Nogueira, E. L., Nolkha, N., Nordstrom, D., Novikov, P., Nugaliyadde, A., O'Donnell, J. L., O'Donoghue, J., O'Neill, L., O'Riordan, E., Oatley, M., Okubo, K., Oliva, E., Oshikawa, H., Ota, Y., Padoan, R., Pagnoux, C., Pan, L., Panaritis, K., Park, J. K., Patel, S., Patil, P., Pazzola, G., Peall, A., Pearce, F., Pehlevan, S., Pereira, L., Pettersson, T., Pineau, C. A., Pirila, L., Poglodek, B., Ponte, C., Prieto-Gonzalez, S., Priya, S. R., Purewal, B., Purschke, S., Putaala, J., Quickert, S., Quincey, V., Raghuvanshi, S., Rajasekhar, L., Ranganathan, D., Rathi, M., Rees, D., Rees, F., Renken, U., Restuccia, G., Rhee, R. L., Rice, B., Robins, D., Robson, J., Rodrigues, M., Romao, V. C., Rotar, C., Ruediger, C., Rutgers, A., A. C., Sa, Saavedra, M. J., Sada, K. -E., Sahbudin, I., Salvarani, C., Sandhu, N., Santos, E., Sato, Y., Schafer, V. S., Schiavon, F., Schmidt, W. A., Segelmark, M., Shahin, A., Sharma, A., Shotton, J., Silva, C., Singer, O. G., Sivasuthan, G., Smolen, S., Solanich-Moreno, X., Boixader, L. S., Song, Y. W., Springer, J., Sreih, A. G., Srivastava, R., Stamp, L. K., Stevens, R., Strbian, D., Sugino, K., Sunderkotter, C., Suppiah, R., Suzuki, K., Szekanecz, Z., Sznajd, J., Taimen, K., Tak, P. P., Takeuchi, T., Takizawa, N., Tames, L., Tan, B. E., Tanaka, M., Tang, M. W., Tatlisumak, T., Tesar, V., Thomas, A., Tian, X., Tokunaga, K., Tombetti, E., Tomsic, M., Toz, B., Tsukamoto, T., Uchida, S., Unal, A. U., Urban, M. L., Usui, J., Vaglio, A., Venkatachalam, S., Vermaak, E., Viswanath, V., Wada, T., Wagh, S., Wallace, D. J., Walters, G., Walz, B., Wan, J., Wang, T., Wang, G., Warrington, K. J., Watts, R. A., Wawrzycka-Adamczyk, K., Weeratunga, P., Weisman, M. H., Wickramasinghe, S., Williams, M., Wojcik, K., Woodruff, L., Xenitidis, T., Yamada, H., Yamagata, K., Yee, C. -S., Yoon, M., Yoshida, K., Yoshifuji, H., Ytterberg, S. R., Yumura, W., Zayed, H., Zeng, X., Zhao, M. -H., Zugaj, A., Zuk, J., İç Hastalıkları, Clinical Haematology, and Translational Immunology Groningen (TRIGR)

Subjects
Male, Outcome, Antineutrophil Cytoplasmic, 030232 urology & nephrology, 0302 clinical medicine, Risk Factors, 80 and over, Pharmacology (medical), Age of Onset, Young adult, Aged, 80 and over, education.field_of_study, age, anti-neutrophil cytoplasmic antibody-associated vasculitis, outcome, Adolescent, Adult, Aged, Anti-Neutrophil Cytoplasmic Antibody-Associated Vasculitis, Antibodies, Antineutrophil Cytoplasmic, Female, Humans, Middle Aged, Morbidity, Prognosis, Retrospective Studies, Risk Assessment, Survival Rate, United Kingdom, Young Adult, Vasculitis, Systemic vasculitis, medicine.medical_specialty, Population, anti-neutrophil cytoplasmic antibody–associated vasculitis, Antibodies, 03 medical and health sciences, Rheumatology, Internal medicine, medicine, education, Anti-neutrophil cytoplasmic antibody–associated vasculitis, Survival rate, Anti-neutrophil cytoplasmic antibody, 030203 arthritis & rheumatology, business.industry, Retrospective cohort study, medicine.disease, Age of onset, business
Abstract

Objectives ANCA-associated vasculitis (AAV) can affect all age groups. We aimed to show that differences in disease presentation and 6 month outcome between younger- and older-onset patients are still incompletely understood. Methods We included patients enrolled in the Diagnostic and Classification Criteria for Primary Systemic Vasculitis (DCVAS) study between October 2010 and January 2017 with a diagnosis of AAV. We divided the population according to age at diagnosis: Results A total of 1338 patients with AAV were included: 66% had disease onset at Conclusion Within 6 months of diagnosis of AAV, patients >65 years of age display a different pattern of organ involvement and an increased risk of significant damage and mortality compared with younger patients.

Published
2021
Full Text
View/download PDF

22. Model-Based Imitation Learning for Urban Driving

Author

Hu, A, Corrado, G, Griffiths, N, Murez, Z, Gurau, C, Yeo, H, Kendall, A, Cipolla, R, and Shotton, J

Subjects
FOS: Computer and information sciences, Computer Science - Robotics, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Robotics (cs.RO)
Abstract

An accurate model of the environment and the dynamic agents acting in it offers great potential for improving motion planning. We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for autonomous driving. Our method leverages 3D geometry as an inductive bias and learns a highly compact latent space directly from high-resolution videos of expert demonstrations. Our model is trained on an offline corpus of urban driving data, without any online interaction with the environment. MILE improves upon prior state-of-the-art by 31% in driving score on the CARLA simulator when deployed in a completely new town and new weather conditions. Our model can predict diverse and plausible states and actions, that can be interpretably decoded to bird's-eye view semantic segmentation. Further, we demonstrate that it can execute complex driving manoeuvres from plans entirely predicted in imagination. Our approach is the first camera-only method that models static scene, dynamic scene, and ego-behaviour in an urban driving environment. The code and model weights are available at https://github.com/wayveai/mile., Comment: NeurIPS 2022

Published
2022
Full Text
View/download PDF

26. Efficient Human Pose Estimation from Single Depth Images

Author

Shotton, J., primary, Girshick, R., additional, Fitzgibbon, A., additional, Sharp, T., additional, Cook, M., additional, Finocchio, M., additional, Moore, R., additional, Kohli, P., additional, Criminisi, A., additional, Kipman, A., additional, and Blake, A., additional

Published
2013
Full Text
View/download PDF

28. Anatomy Detection and Localization in 3D Medical Images

Author

Criminisi, A., primary, Robertson, D., additional, Pauly, O., additional, Glocker, B., additional, Konukoglu, E., additional, Shotton, J., additional, Mateus, D., additional, Martinez Möller, A., additional, Nekolla, S. G., additional, and Navab, N., additional

Published
2013
Full Text
View/download PDF

44. Depth-Based Hand Pose Estimation: Methods, Data, and Challenges

Author

Supančič, JS, Rogez, G, Yang, Y, Shotton, J, Ramanan, D, Supančič, JS, Rogez, G, Yang, Y, Shotton, J, and Ramanan, D

Abstract

Hand pose estimation has matured rapidly in recent years. The introduction of commodity depth sensors and a multitude of practical applications have spurred new advances. We provide an extensive analysis of the state-of-the-art, focusing on hand pose estimation from a single depth frame. To do so, we have implemented a considerable number of systems, and have released software and evaluation code. We summarize important conclusions here: (1) Coarse pose estimation appears viable for scenes with isolated hands. However, high precision pose estimation [required for immersive virtual reality and cluttered scenes (where hands may be interacting with nearby objects and surfaces) remain a challenge. To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes. (2) Many methods evaluate themselves with disparate criteria, making comparisons difficult. We define a consistent evaluation criteria, rigorously motivated by human experiments. (3) We introduce a simple nearest-neighbor baseline that outperforms most existing systems. This implies that most systems do not generalize beyond their training sets. This also reinforces the under-appreciated point that training data is as important as the model itself. We conclude with directions for future progress.

Published
2018

46. Training CNNs with Low-Rank Filters for Efficient Image Classification

Author

Ioannou, Y., Robertson, D., Shotton, J., Roberto Cipolla, and Criminisi, A.

Subjects
FOS: Computer and information sciences, 0209 industrial biotechnology, Low-Rank, Neural Networks, Computer Vision and Pattern Recognition (cs.CV), Computer Vision, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Neural and Evolutionary Computing, 02 engineering and technology, Machine Learning (cs.LG), Computer Science - Learning, 020901 industrial engineering & automation, Deep Learning, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Neural and Evolutionary Computing (cs.NE)
Abstract

We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more efficient versions, we learn a set of small basis filters from scratch; during training, the network learns to combine these basis filters into more complex filters that are discriminative for image classification. To train such networks, a novel weight initialization scheme is used. This allows effective initialization of connection weights in convolutional layers composed of groups of differently-shaped filters. We validate our approach by applying it to several existing CNN architectures and training these networks from scratch using the CIFAR, ILSVRC and MIT Places datasets. Our results show similar or higher accuracy than conventional CNNs with much less compute. Applying our method to an improved version of VGG-11 network using global max-pooling, we achieve comparable validation accuracy using 41% less compute and only 24% of the original VGG-11 model parameters; another variant of our method gives a 1 percentage point increase in accuracy over our improved VGG-11 model, giving a top-5 center-crop validation accuracy of 89.7% while reducing computation by 16% relative to the original VGG-11 model. Applying our method to the GoogLeNet architecture for ILSVRC, we achieved comparable accuracy with 26% less compute and 41% fewer model parameters. Applying our method to a near state-of-the-art network for CIFAR, we achieved comparable accuracy with 46% less compute and 55% fewer parameters., Published as a conference paper at ICLR 2016. v3: updated ICLR status. v2: Incorporated reviewer's feedback including: Amend Fig. 2 and 5 descriptions to explain that there are no ReLUs within the figures. Fix headings of Table 5 - Fix typo in the sentence at bottom of page 6. Add ref. to Predicting Parameters in Deep Learning. Fix Table 6, GMP-LR and GMP-LR-2x had incorrect numbers of filters

Published
2016
Full Text
View/download PDF

48. Real-time RGB-D camera relocalization via randomized ferns for keyframe encoding

Author

Glocker, B, Shotton, J, Criminisi, A, and Izadi, S

Subjects
Technology, TRACKING, Science & Technology, Computer Science, tracking recovery, marker-free augmented reality, MONOCULAR SLAM, 0801 Artificial Intelligence and Image Processing, Software Engineering, Computer Science, Software Engineering, Camera relocalization, dense tracking and mapping, 0802 Computation Theory and Mathematics
Abstract

Recovery from tracking failure is essential in any simultaneous localization and tracking system. In this context, we explore an efficient keyframe-based relocalization method based on frame encoding using randomized ferns. The method enables automatic discovery of keyframes through online harvesting in tracking mode, and fast retrieval of pose candidates in the case when tracking is lost. Frame encoding is achieved by applying simple binary feature tests which are stored in the nodes of an ensemble of randomized ferns. The concatenation of small block codes generated by each fern yields a global compact representation of camera frames. Based on those representations we define the frame dissimilarity as the block-wise hamming distance (BlockHD). Dissimilarities between an incoming query frame and a large set of keyframes can be efficiently evaluated by simply traversing the nodes of the ferns and counting image co-occurrences in corresponding code tables. In tracking mode, those dissimilarities decide whether a frame/pose pair is considered as a novel keyframe. For tracking recovery, poses of the most similar keyframes are retrieved and used for reinitialization of the tracking algorithm. The integration of our relocalization method into a hand-held KinectFusion system allows seamless continuation of mapping even when tracking is frequently lost.

Published
2014

49. Decision Forests : A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-supervised Learning

Author

Criminisi, Antonio, Konukoglu, Ender, Shotton, J., Criminisi, Antonio, Konukoglu, Ender, and Shotton, J.

Subjects
Decision trees, Expert systems (Computer science)--Design, Decision support systems, Logic programming, Machine learning--Decision making
Abstract

Presents a unified, efficient model of random decision forests which can be used in a number of applications such as scene recognition from photographs, object recognition in images, automatic diagnosis from radiological scans and document analysis.

Published
2012

Catalog

Books, media, physical & digital resources
See catalog results