Niels da Vitoria Lobo

@conference{Khan2022,

title = {Weakly Supervised Grounding for VQA in Vision-Language Transformers},

author = {Aisha Urooj Khan and Hilde Kuehne and Chuang Gan and Niels Da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/1011.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/1011-supp.pdf

https://github.com/aurooj/WSG-VQA-VLTransformers

https://youtu.be/dekmVb6lq3I},

year  = {2022},

date = {2022-10-23},

urldate = {2022-10-23},

booktitle = {European Conference on Computer Vision},

abstract = {Transformers for visual-language representation learning have been getting a lot of interest and shown tremendous performance on visual question answering (VQA) and grounding. However, most systems that show good performance of those tasks still rely on pre-trained object

detectors during training, which limits their applicability to the object classes available for those detectors. To mitigate this limitation, this paper

focuses on the problem of weakly supervised grounding in the context of visual question answering in transformers. Our approach leverages

capsules by transforming each visual token into a capsule representation in the visual encoder; it then uses activations from language self-attention layers as a text-guided selection module to mask those capsules before they are forwarded to the next layer. We evaluate our approach on the challenging GQA as well as VQA-HAT dataset for VQA grounding. Our experiments show that: while removing the information of masked

objects from standard transformer architectures leads to a significant drop in performance, the integration of capsules significantly improves the grounding ability of such systems and provides new state-of-the-art results compared to other approaches in the field.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Khan2021b,

title = {Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules},

author = {Aisha Urooj Khan and Hilde Kuehne and Kevin Duarte and Chuang Gan and Niels Da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Found-a-Reason-for-me.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Found-a-Reason-for-me_Supp.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/cvpr21_poster_v2.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/cvpr_2021_5min.mp4},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Khan2020b,

title = {MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering},

author = {Aisha Urooj Khan and Amir Mazaheri and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_MMFT-BERT.pdf},

year  = {2020},

date = {2020-11-16},

booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, EMNLP},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sharghi2020,

title = {Text Synopsis Generation for Egocentric Videos},

author = {Aidean Sharghi and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/05/Publications_Text-Synopsis-Generation-for-Egocentric-Videos.pdf

https://youtu.be/Z2Rpy7MC7QI},

year  = {2020},

date = {2020-05-08},

booktitle = {International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Prokaj2017,

title = {Scale Space Based Grammar for Hand Detection},

author = {Jan Prokaj and Niels da Vitoria Lobo },

year  = {2017},

date = {2017-08-08},

booktitle = {Springer Lecture Notes in Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Gupta2013b,

title = {Markerless Tracking And Gesture Recognition Using Polar Correlation of Camera Optical Flow},

author = {P. Gupta and Niels da Vitoria Lobo and J.J. LaViola and Jon Harter and Phillip Napieralski },

year  = {2013},

date = {2013-04-01},

booktitle = { Machine Vision and Applications Journal},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Li2010b,

title = { GAUSS: An NSF CSUMS project at UCF},

author = {Xin Li and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/05/Publications_GAUSS-An-NSF-CSUMS-Project-at-UCF.pdf},

year  = {2010},

date = {2010-06-22},

booktitle = {2nd International Conference on Education Technology and Computer (ICETC), Shanghai, China, June 22-24},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Schwarz2007,

title = {The Camera-driven Interactive Table},

author = {Chris Schwarz and Niels da Vitoria Lobo },

year  = {2007},

date = {2007-08-03},

booktitle = {IEEE WACV,},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Smith2005,

title = {Temporal Boost for Event Recognition},

author = {Paul Smith and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/TemporalBoost-ICCV2005.pdf},

year  = {2005},

date = {2005-11-20},

publisher = {IEEE ICCV},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Batz2005,

title = {Visual System for Monitoring Medication Intake},

author = {D. Batz and M. Batz and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2005},

date = {2005-11-05},

publisher = {Procs. Canadian Conference on Computer and Robot Vision},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Garcia2005,

title = {Finding Heads in Single Images},

author = {J. Garcia and Niels da Vitoria Lobo and Mubarak Shah and J. Feinstein},

year  = {2005},

date = {2005-11-04},

publisher = {Procs. Canadian Conference on Computer and Robot Vision},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Schwarz2005b,

title = { Hand Pose Detection using Segments},

author = {Chris Schwarz and Niels da Vitoria Lobo },

year  = {2005},

date = {2005-05-04},

booktitle = {Proc. CRV2005},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Garcia2005b,

title = { Finding Heads in Single Images},

author = {Justin Garcia and Niels da Vitoria Lobo and Mubarak Shah and J. Feinstein },

year  = {2005},

date = {2005-05-03},

booktitle = {Proc. CRV},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Batz2005b,

title = {Visual System for Monitoring Medication Intake},

author = {David Batz and Michael Batz and Niels da Vitoria Lobo and Mubarak Shah },

year  = {2005},

date = {2005-05-02},

booktitle = {Proc CRV},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Schwarz2005,

title = {Hand Pose Detection using Segments},

author = {Chris Schwarz and Niels da Vitoria Lobo},

year  = {2005},

date = {2005-05-01},

booktitle = {CRV},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wells2004,

title = {Automatic Visual Tracking for Analysis of Lifting},

author = {Michael Wells and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2004},

date = {2004-11-28},

publisher = {Irish Machine Vision and Image Processing Conference},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Smith2004,

title = {Integrating and Employing Multiple Levels of Zoom for Activity Recognition},

author = {Paul Smith and Mubarak Shah and Niels da Vitoria Lobo},

url = {https://www.crcv.ucf.edu/papers/smith_shah_lobo_cvpr_2004.pdf},

year  = {2004},

date = {2004-11-18},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wells2004b,

title = {Automatic Visual Tracking for Analysis of Lifting},

author = {Michael Wells and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2004},

date = {2004-08-05},

booktitle = {Proc. IMVIP},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{III2004,

title = {Object Tracking in Low Frame-Rate Video},

author = {Alfred K. Levy III and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2004},

date = {2004-08-02},

booktitle = {Proc. IMVIP2004},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Smith2003b,

title = {Determining Driver Visual Attention with One Camera},

author = {Paul Smith and Mubarak Shah and Niels da Vitoria Lobo},

year  = {2003},

date = {2003-10-08},

booktitle = {IEEE Transactions on Pattern Analysis and Machine Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Datta2003b,

title = {Novel Feature Vector for Image Authentication},

author = {Ankur Datta and Niels da Vitoria Lobo and John Leeson },

year  = {2003},

date = {2003-08-08},

booktitle = {ICME},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Bhatt2003,

title = { Automatic recognition of a baby gesture},

author = {Jigna Bhatt and Niels da Vitoria Lobo and Mubarak Shah and Bebis G. },

year  = {2003},

date = {2003-08-06},

booktitle = {ICTAI},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Datta2003,

title = {Person-on-Person Violence Detection in Moving and Stationary Camera Videos},

author = {Ankur Datta and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2003},

date = {2003-08-06},

booktitle = { IASTED conference},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Dever2002,

title = {Automatic Visual Recognition of Armed Robbery},

author = {Jaime Dever and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/robbery.pdf},

year  = {2002},

date = {2002-12-27},

publisher = {IEEE International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Datta2002,

title = {Person-on-Person Violence Detection in Video Data},

author = {Ankur Datta and Mubarak Shah and Niels Da Vitoria Lobo},

url = {https://www.crcv.ucf.edu/papers/ICPR_2002.pdf},

year  = {2002},

date = {2002-12-27},

publisher = {IEEE International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Russo2002,

title = {A Computer Vision System for Monitoring Production of Fast Food},

author = {Richard Russo and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/accv90.pdf},

year  = {2002},

date = {2002-12-25},

publisher = {Asian Conference on Computer Vision},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{A.2002,

title = {Wheelchair Detection in a Calibrated Environment},

author = {Myles A. and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2002},

date = {2002-08-12},

booktitle = {ACCV},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Datta2002b,

title = { Person-on-Person Violence Detection in Video Data},

author = {Ankur Datta and Mubarak Shah and Niels da Vitoria Lobo },

year  = {2002},

date = {2002-08-09},

booktitle = {International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Dever2002b,

title = {Automatic Visual Recognition of Armed Robbery},

author = {Jaime Dever and Niels da Vitoria Lobo and Mubarak Shah },

year  = {2002},

date = {2002-08-08},

booktitle = {IEEE International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Russo2002b,

title = {A Computer Vision System for Monitoring Production of Fast Food},

author = {Richard Russo and Niels da Vitoria Lobo and Mubarak Shah },

year  = {2002},

date = {2002-01-11},

booktitle = {Asian Conference on Computer Vision},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{III2002b,

title = {Flame Recognition in Video,},

author = {Walter Phillips III and Mubarak Shah and Niels da Vitoria Lobo},

year  = {2002},

date = {2002-01-01},

booktitle = {Pattern Recognition Letters},

volume = {23},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{B.2001,

title = {Human identification through body measurements},

author = {Bracewell D. B. and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2001},

date = {2001-08-06},

booktitle = {Proceedings of Computers and Their Applications},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wallick2001c,

title = {A System for Placing Videotaped and Digital Lectures Online},

author = {M. Wallick and Niels da Vitoria Lobo and Mubarak Shah},

year  = {2001},

date = {2001-08-03},

booktitle = {International Symposium on Intelligent Multimedia, Video and Speech},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wallick2001b,

title = {Computer Vision Framework for Analyzing Projections from Video of Lectures},

author = {M. Wallick and Niels da Vitoria Lobo and Mubarak Shah },

year  = {2001},

date = {2001-06-01},

booktitle = {International Journal of Computers and Their Applications - Special Issue on Intelligent Systems},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Smith2000,

title = {Monitoring Head/Eye Motion for Driver Alertness with One Camera},

author = {Paul Smith and Mubarak Shah and Niels da Vitoria Lobo},

url = {https://www.crcv.ucf.edu/papers/1315_smith.pdf},

year  = {2000},

date = {2000-12-28},

publisher = {Fifteenth IEEE International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wu2000,

title = {A Virtual 3D Blackboard: 3D Finger Tracking using a single camera},

author = {Andrew Wu and Mubarak Shah and Niels da Vitoria Lobo},

url = {https://www.crcv.ucf.edu/papers/fg2000.pdf},

year  = {2000},

date = {2000-12-27},

publisher = {FG'2000 Fourth IEEE International Conference on Automatic Face and Gesture Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wallick2000,

title = {Computer Vision Framework for Analyzing Projections from Video of Lectures},

author = {M. Wallick and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/icisfinal.pdf},

year  = {2000},

date = {2000-12-27},

publisher = {ISCA 9th International Conference for Intelligent Systems},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Haering2000,

title = {A Framework for Designing Event Detectors,},

author = {Niels Haering and Niels da Vitoria Lobo and Richard Qian and Ibrahim Sezan},

year  = {2000},

date = {2000-12-24},

publisher = {Asian Conference on Computer Vision},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}