Search
Search Funnelback University
- Refined by:
- Date: 2018
Did you mean people alumni |u:mi.eng.cam.ac.uk?
1 -
50 of
167
search results for People aliens |u:mi.eng.cam.ac.uk
where 0
match all words and 167
match some words.
Results that match 1 of 2 words
-
UNIX Tutorial for Beginners
mi.eng.cam.ac.uk/~wjb31/MLMI/unixtut/28 Sep 2018: UNIX was originally developed at Bell Laboratories as a private research project by a small group of people. -
PowerPoint プレゼンテーション
mi.eng.cam.ac.uk/UKSpeech2017/posters/e_tsunoo.pdf3 Jul 2018: More than 70 people die every day while fishing at sea. -
Using Wizard-of-Oz simulations to bootstrap…
mi.eng.cam.ac.uk/~sjy/papers/wiyo03.pdf20 Feb 2018: We choose human/wizard rather than human/human dialogs as people behave differently toward (what they perceive to be) machines and other people as discussed in Jönsson and Dahlbick, 1988 and -
Photo-Realistic Expressive Text to Talking Head Synthesis Vincent…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2013-Interspeech-EVTTS.pdf13 Mar 2018: Expressiveness isan important aspect of any direct interaction between people.The expressions convey additional information to the listenerbeyond the spoken words. ... Twenty people wereasked to identify the emotions depicted in the original au-dio/video -
Photo-Realistic Expressive Text to Talking Head Synthesis Vincent…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2013-Interspeech-Talking-Head.pdf13 Mar 2018: Expressiveness isan important aspect of any direct interaction between people.The expressions convey additional information to the listenerbeyond the spoken words. ... Twenty people wereasked to identify the emotions depicted in the original au-dio/video -
Unsupervised Bayesian Detection of Independent Motion in Crowds…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2006-CVPR-Brostow-motionincrowds.pdf13 Mar 2018: The algo-rithm is tested to give quantitative results on crowds of upto 33 people. ... 16] D. Ramanan and D. A. Forsyth. Finding and tracking people from the bottomup. -
An information-theoretic approach to facerecognition from face motion …
mi.eng.cam.ac.uk/~cipolla/publications/article/2006-IVC-Arandjelovic.pdf13 Mar 2018: Recognition rate of 98% was achieved on a database of100 people under varying illumination. ... Acknowledgements. We would like to thank the Toshiba Corporation for their kind support for our re-search, the people from the University of Cambridge -
main
mi.eng.cam.ac.uk/~cipolla/publications/article/2016-CVIU-EVTTS-autism.pdf13 Mar 2018: However, complex natural facial51expressions that present diculties for people with ASC in everyday life are52challenging to simulate using robotics.53. ... Lack of attention to social information (eyes141and people) could be a key contributor to these -
Face Recognition from Face Motion Manifolds using Robust…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2004-FPIV-Arandjelovic-face.pdf13 Mar 2018: Recognition ratesof 97–100% are consistently achieved on databases of 35–90 people. ... Shown is the identificationrate (%) for five databases of 35 people (1–5) and one of 90 (6). -
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-MVA-Conde.pd…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-MVA-Conde.pdf13 Mar 2018: It has been tested in real conditions with a 3D database (FRAV3D), at present composed by 51 people (714 total captures) in different pose conditions. -
ON-LINE POLICY OPTIMISATION OF BAYESIAN SPOKEN DIALOGUE SYSTEMS…
mi.eng.cam.ac.uk/~sjy/papers/gbhk13.pdf20 Feb 2018: 3.4. Amazon MTurk service. In order to evaluate or train a policy with real people we used crowd-sourcing, for which we used the Amazon MTurk service in a -
Real user evaluation of spoken dialogue systems using Amazon ...
mi.eng.cam.ac.uk/~sjy/papers/jkgm11.pdf20 Feb 2018: The ultimategoal should be to design and deploy such dialogue systems thatthey would be used by people genuinely interested in the serviceand to reach a volume of calls that would allow -
On Person Authentication by Fusing Visual and Thermal Face ...
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2006-AVSS-Arandjelovic-authentication.pdf13 Mar 2018: The practical importance of this can be seen bynoting that in the US in 2000 roughly 96 million people, or34% of the total population, wore prescription glasses [18]. ... 1-to-N and 1-to-1 matching scenarios. In the former case,we assumed that test data -
CHARLES et al.: EXTRACTING THE X FACTOR IN HUMAN ...
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2017-BMVC-human-segmentation.pdf13 Mar 2018: c) shows per-class IOU comparison on Unite the People S31. YouTube Pose [7]. ... OnUnite the People, these scores are shown as averages over left-right body parts. -
tech.dvi
mi.eng.cam.ac.uk/~sjy/papers/bghk13.pdf20 Feb 2018: A general background model wasnot. found to be helpful as the things that people tend to say in thecon-text of the dialogue system are very limited, and well covered bydata -
techreport_20060422MJ.dvi
mi.eng.cam.ac.uk/~cipolla/publications/article/2006-Eurographics-semantic.pdf13 Mar 2018: Our primary contributionis a new method for creating images of specific thingsand people, with minimal human effort. ... semantic labels such as proper names of people, andcan be supplemented with copy-pasted islands of pixelsfor categories that lack -
TAN, BUDVYTIS, CIPOLLA: INDIRECT DEEP STRUCTURED LEARNING 1 Indirect…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2017-BMVC-3D-body-indirect.pdf13 Mar 2018: artificially generated 3D human body images (using SMPL [2]) and on real images from theUnite the People dataset [9]. ... within the range of values ob-served in the Unite The People dataset [9]. -
hci09.dvi
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2009-HCI-Stenger.pdf13 Mar 2018: 5.2 Face recognition experimentsWe have evaluated the face recognition performance usinga data set containing 5 people (10 sequences per person, 50frames per sequence). ... Although the trackingexperiments in this paper show results on a relatively -
An information-theoretic approach to facerecognition from face motion …
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2006-IVC-Arandjelovic.pdf13 Mar 2018: Recognition rate of 98% was achieved on a database of100 people under varying illumination. ... Acknowledgements. We would like to thank the Toshiba Corporation for their kind support for our re-search, the people from the University of Cambridge -
Use of Graphemic Lexicons for Spoken Language Assessment K.M. ...
mi.eng.cam.ac.uk/~ar527/knill_is2017.pdf15 Jun 2018: 1. IntroductionBy 2020 the number of people worldwide using or learningEnglish as an additional language is expected to exceed 1.5billion [1]. -
05-02_178
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2007-MVA-Thayananthan.pdf13 Mar 2018: method was tested on 40 frames of a real 15 Hzvideo (resolution 160x120), where two people cross infront of a stationary background. -
crosseval_diff-reward2b.ps
mi.eng.cam.ac.uk/~sjy/papers/kgjm10.pdf20 Feb 2018: An extensive analysis of the an-notations from three different people revealed ahigh level of inter-annotator agreement (rangingfrom 0.81 to 0.94, depending on which pair of an-notations -
main
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2016-CVIU-EVTTS-autism.pdf13 Mar 2018: However, complex natural facial51expressions that present diculties for people with ASC in everyday life are52challenging to simulate using robotics.53. ... Lack of attention to social information (eyes141and people) could be a key contributor to these -
Impact of ASR Performance on Free Speaking Language Assessment ...
mi.eng.cam.ac.uk/~ar527/knill_is2018.pdf15 Jun 2018: 1. IntroductionMore than 1.5 billion people are predicted to be learning En-glish as an additional language by 2020 [1]. -
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2005-MVA-…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2005-MVA-Conde.pdf13 Mar 2018: It has been tested in real conditions with a 3D database (FRAV3D), at present composed by 51 people (714 total captures) in different pose conditions. -
On Person Authentication by Fusing Visual and Thermal Face ...
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2006-AVSS-Arandjelovic-authentication.pdf13 Mar 2018: The practical importance of this can be seen bynoting that in the US in 2000 roughly 96 million people, or34% of the total population, wore prescription glasses [18]. ... 1-to-N and 1-to-1 matching scenarios. In the former case,we assumed that test data -
N-BEST ERROR SIMULATION FOR TRAINING SPOKEN DIALOGUE SYSTEMS Blaise…
mi.eng.cam.ac.uk/~sjy/papers/thgt12.pdf20 Feb 2018: Rep.,MIT, 2003, http://research.microsoft.com/en-us/um/people/minka/papers/dirichlet/. [19] F. Jurcicek, B. Thomson, and S. Young, “Reinforcement learn-ing for parameter estimation in statistical spoken -
PRLETTERS-D-12-00247R1[1]
mi.eng.cam.ac.uk/~cipolla/publications/article/2013-PR-bipedal-motion.pdf13 Mar 2018: 15. Figure 8: Results on Sequence II. Detection of bipedal motion of two people walkingacross the scene from opposite directions (from top to bottom). ... S., Cutler, R., 2002. Motion-based recognition514of people in eigengait space. In: Proc. -
bmvc08.dvi
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2008-BMVC-gesture-interface.pdf13 Mar 2018: people may be within the camera’sview. ... 5.1 Face recognition experiments. We have evaluated the face recognition performance using a data set containing 5 people(10 sequences per person, 50 frames per sequence). -
techreport_20060422MJ.dvi
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2006-Eurographics-semantic.pdf13 Mar 2018: Our primary contributionis a new method for creating images of specific thingsand people, with minimal human effort. ... semantic labels such as proper names of people, andcan be supplemented with copy-pasted islands of pixelsfor categories that lack -
Semantic object classes in video: A high-definition ground truth…
mi.eng.cam.ac.uk/~cipolla/publications/article/2009-PR-car-video-database.pdf13 Mar 2018: They include fixed objects, typesof road surface, moving objects (including vehicles and people),. ... People smaller than that in image-space are often not detected (shown as red rectangles). -
C:/SFWDoc/Academic/Publications/2005/BMVC_2005/FinalPaper/bmvc_05_sfwo…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-BMVC-Wongsf-realtime.pdf13 Mar 2018: Research in sign language recogni-tion is therefore useful in building an interface between deaf and hearing people, and alsoin developing novel human-computer interfaces. ... These 5 hand shapes were selected because people can easilytell them apart -
An Illumination Invariant Face Recognition System forAccess Control…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2004-BMVC-Arandjelovic-invariant.pdf13 Mar 2018: KLD wasalso criticized for being asymmetric [1, 9]. More subtly, both approaches have the disadvantage of comparing whole face distributions, whichhas the implicit assumption that for the same people we expect ... It wasshown that our method consistently -
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, JANUARY…
mi.eng.cam.ac.uk/~sjy/papers/gayo14.pdf20 Feb 2018: The results were then averagedand presented with one standard error. 5) The MTurk Amazon Service: In order to evaluate differ-ent policies with real people we recruited subjects using theAmazon MTurk -
TAN, BUDVYTIS, CIPOLLA: INDIRECT DEEP STRUCTURED LEARNING 1 Indirect…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2017-BMVC-3D-body-indirect.pdf13 Mar 2018: artificially generated 3D human body images (using SMPL [2]) and on real images from theUnite the People dataset [9]. ... within the range of values ob-served in the Unite The People dataset [9]. -
Efficiently Combining Contour and TextureCues for Object Recognition…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2008-BMVC-Shotton.pdf13 Mar 2018: We highlight the categorization im-provements for bikes (side and front), people, cups, and cars ( 23 rear), and the detectionimprovements for bikes (side) and cars (front). ... Horses (front). People. Cars (front). Cows (front). Cars ( rear). Cups. -
05-02_178
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2007-MVA-Thayananthan.pdf13 Mar 2018: method was tested on 40 frames of a real 15 Hzvideo (resolution 160x120), where two people cross infront of a stationary background. -
Towards Person Authentication by Fusing Visual and Thermal…
mi.eng.cam.ac.uk/~cipolla/publications/contributionToEditedBook/2007-MM-chapter1.pdf13 Mar 2018: 5. The practical importance of this canbe seen by noting that in the US in 2000 roughly 96 million people, or 34% of the total population, woreprescription glasses [42]. ... In theformer case, we assumed that test data corresponded to one of people in -
Spatio-Temporal Clustering of Probabilistic Region Trajectories Fabio …
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2011-ICCV-Galasso-ST.pdf13 Mar 2018: a vision system may be employed to detect. pieces of clothing, human silhouettes, or a moving crowd.Contemporary people detectors achieve this goal by. ... As discussed in Sec. 4, our modelmay be employed to learn different motion patterns but thisstudy -
Co-occurrence Flow for Pedestrian Detection
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2011-ICIP-pedestrian-detection.pdf13 Mar 2018: In BMVC, 2009. [20] C. Wojek and B. Schiele. A performance evaluation of single and multi-feature people detection. -
PRLETTERS-D-12-00247R1[1]
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2013-PR-bipedal-motion.pdf13 Mar 2018: 15. Figure 8: Results on Sequence II. Detection of bipedal motion of two people walkingacross the scene from opposite directions (from top to bottom). ... S., Cutler, R., 2002. Motion-based recognition514of people in eigengait space. In: Proc. -
bmvc08.dvi
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2008-BMVC-gesture-interface.pdf13 Mar 2018: people may be within the camera’sview. ... 5.1 Face recognition experiments. We have evaluated the face recognition performance using a data set containing 5 people(10 sequences per person, 50 frames per sequence). -
Model-Based 3D Tracking of an Articulated Hand B. Stenger ...
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2001-CVPR-Stenger-hand.pdf13 Mar 2018: Springer-Verlag, London, 1998. [4] C. Bregler and J. Malik. Tracking people with twists and ex-ponential maps. -
Multi-Sensory Face Biometric Fusion (for Personal Identification)…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2006-OTCBVS-Arandjelovic-fusion.pdf13 Mar 2018: 5. Thepractical importance of this can be seen by noting that in theUS in 2000 roughly 96 million people, or 34% of the totalpopulation, wore prescription glasses [36]. ... 17] G. Friedrich and Y. Yeshurun. Seeing people in the dark: face recog-nition in -
nips08_tk_final.dvi
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2008-NIPS-MCBoost.pdf13 Mar 2018: Acknowledgements. The authors are grateful to many people who have helped by proofreading drafts and providingcomments and suggestions. -
Large scale labelled video data augmentation for semantic…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2017-ICCV-label-propagation.pdf13 Mar 2018: As a part of our evaluation effort weinclude the CamVid-Instance dataset consisting of instancelabels for people and cars from the original CamVid [6]dataset. ... Row (a) on the right section of this figure contains three image and corresponding instance -
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2015-ICCV-relocalisation.pdf13 Mar 2018: For example the scene may include dynamicobjects like people and cars or experience changing weatherconditions. ... The last observation is that PoseNet has an attenuated re-sponse to people and other noisy objects, effectively mask-ing them. -
Sparse and Semi-supervised Visual Mapping with the S3GP Oliver ...
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2006-CVPR-Williams-sparse.pdf13 Mar 2018: Text input with a one-dimensionalcontinuous signal is possible via the Dasher system [19] andthese simple uses for the S3GP offer a light-weight com-munication device for people that are ... people with repetitive strain injuries. -
system.dvi
mi.eng.cam.ac.uk/~sjy/papers/heyo06.pdf20 Feb 2018: The SACTI corpus consists of task-. oriented dialogues between two people in a simulated ASR channel. -
ADAPTATION OF AN EXPRESSIVE SINGLE SPEAKER DEEP NEURAL NETWORKSPEECH…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2018-ICASSP-speaker-adaptation.pdf3 May 2018: We think this is not areflection on the results but rather a reflection on the difficulty withwhich people can judge the similarity of expressions.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.