Filters








713 Hits in 2.8 sec

(De)constructing ethics for autonomous cars: A case study of Ethics Pen-Testing towards "AI for the Common Good"

Bettina Berendt
2020 International Review of Information Ethics  
Via four lead questions, the concept of Ethics Pen-Testing (EPT) identifies challenges and pitfalls when determining, from an AI point of view, what the Common Good is and how it can be enhanced by AI.  ...  EPT is applicable to various artefacts that have ethical impact, including designs for or implementations of specific AI technology, and requirements engineering methods for eliciting which ethical settings  ...  For example, chassis shapes exist that reduce the impact of a crash on pedestrians 11 .  ... 
doi:10.29173/irie381 fatcat:e7z7newis5hyvjkvkn4pnoeyc4

Stereo- and neural network-based pedestrian detection

L. Zhao, C.E. Thorpe
2000 IEEE transactions on intelligent transportation systems (Print)  
Third, we use intensity gradients of the candidate sub-images as input to a trained neural network for pedestrian recognition.  ...  Index Terms-Driver assistance system, neural networks, object detection, pedestrian detection, range image segmentation, stereo vision.  ...  ACKNOWLEDGMENT The authors would like to thank the reviewers for their helpful comments and suggestions.  ... 
doi:10.1109/6979.892151 fatcat:unxhcuoj3zdldf5yztafuvgaci

LCollision: Fast Generation of Collision-Free Human Poses using Learned Non-Penetration Constraints [article]

Qingyang Tan, Zherong Pan, Dinesh Manocha
2021 arXiv   pre-print
To the best of our knowledge, LCollision is the first approach that accelerates collision detection and resolves penetrations using a neural network.  ...  These two components of our architecture are used as the objective function and surrogate hard constraints in a constrained optimization for collision-free human pose generation.  ...  new poses from a small set of examples via shape embedding.  ... 
arXiv:2011.03632v4 fatcat:44aaqt2r5ffnzkfycn5lxc3uwq

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
High-Resolution Network for Multi-Scale Pedestrian Detection DAY 3 -Jan 14, 2021 Li, Gang; Zhang, Shanshan; Yang, Jian 2537 Nighttime Pedestrian Detection Based on Feature Attention and Transformation  ...  Pedestrian Detection from Motion in Temporal Domain DAY 1 -Jan 12, 2021 Qammaz, Ammar; Argyros, Antonis 1920 Occlusion-Tolerant and Personalized 3D Human Pose Estimation in RGB Images DAY  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

TripVista: Triple Perspective Visual Trajectory Analytics and its application on microscopic traffic data at a road intersection

Hanqi Guo, Zuchao Wang, Bowen Yu, Huijing Zhao, Xiaoru Yuan
2011 2011 IEEE Pacific Visualization Symposium  
Improved ThemeRiver, embedded with glyphs indicating directional information, and multiple scatterplots with time as horizontal axes illustrate temporal information of the traffic flows.  ...  two-level time range selection; (e) Control panel for system parameter settings and data classification.  ...  ACKNOWLEDGEMENTS The authors thank the anonymous reviewers for their invaluable comments and suggestions. This work is supported by National Natural Science Foundation of China  ... 
doi:10.1109/pacificvis.2011.5742386 dblp:conf/apvis/GuoWYZY11 fatcat:5zfsetaut5cdlnesn44izepxsq

Recurrent Network Models for Human Dynamics [article]

Katerina Fragkiadaki, Sergey Levine, Panna Felsen, Jitendra Malik
2015 arXiv   pre-print
The ERD model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers.  ...  For human pose labeling, ERD outperforms a per frame body part detector by resolving left-right body part confusions.  ...  Acknowledgements We would like to thank Jeff Donahue and Philipp Krähenbühl for useful discussions. We gratefully acknowledge NVIDIA corporation for the donation of K40 GPUs for this research.  ... 
arXiv:1508.00271v2 fatcat:w2me3ddf4fcfnmjf7yk55n5aje

Recurrent Network Models for Human Dynamics

Katerina Fragkiadaki, Sergey Levine, Panna Felsen, Jitendra Malik
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
The ERD model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers.  ...  For human pose labeling, ERD outperforms a per frame body part detector by resolving left-right body part confusions.  ...  Acknowledgements We would like to thank Jeff Donahue and Philipp Krähenbühl for useful discussions. We gratefully acknowledge NVIDIA corporation for the donation of K40 GPUs for this research.  ... 
doi:10.1109/iccv.2015.494 dblp:conf/iccv/FragkiadakiLFM15 fatcat:r2b2wbv2ordbneksnoji4ix2by

A Situationally Aware Voice-commandable Robotic Forklift Working Alongside People in Unstructured Outdoor Environments

Matthew R. Walter, Matthew Antone, Ekapol Chuangsuwanich, Andrew Correa, Randall Davis, Luke Fletcher, Emilio Frazzoli, Yuli Friedman, James Glass, Jonathan P. How, Jeong hwan Jeon, Sertac Karaman (+4 others)
2014 Journal of Field Robotics  
The first is a multimodal interface that allows users to efficiently convey task-level commands to the robot using a combination of pen-based gestures and natural language speech.  ...  We still require invariance to camera pose and lighting variations, but not to intrinsic within-class variability, which allows us to build models from significantly fewer examples.  ...  Pedestrians who approach too closely cause the robot to pause. Planning and Control The most basic mobility requirement for the robot is to move safely from a starting pose to its destination pose.  ... 
doi:10.1002/rob.21539 fatcat:2rrq5dl3zzanta6po3jczl2hsu

Development of Test Equipment for Pedestrian-Automatic Emergency Braking Based on C-NCAP (2018)

Zhiqiang Song, Libo Cao, Clifford C. Chou
2020 Sensors  
In order to evaluate the effectiveness of a pedestrian-automatic emergency braking (PAEB) system on pedestrian protection, a set of PAEB test equipment was developed according to the test requirement of  ...  Subsequently, the performance of the AEB of a vehicle under test (VUT) was conducted and the score for star-rating to evaluate the performance level of AEB calculated.  ...  For accurate detection, the dummy target should have pedestrian walking postures.  ... 
doi:10.3390/s20216206 pmid:33143319 pmcid:PMC7663537 fatcat:k67l5bpnkbdgxawabgipfcjzhu

Deep Learning for IoT Big Data and Streaming Analytics: A Survey [article]

Mehdi Mohammadi, Ala Al-Fuqaha, Sameh Sorour, Mohsen Guizani
2018 arXiv   pre-print
Finally, we shed light on some challenges and potential directions for future research.  ...  The potential of using emerging DL techniques for IoT data analytics are then discussed, and its promises and challenges are introduced.  ...  Furthermore, self-driving cars use DNNs in performing many tasks, such as detecting pedestrians, traffic signs, obstacles, etc.  ... 
arXiv:1712.04301v2 fatcat:kr64lst37rhlfcpaxckgzlozvu

Computer Vision and Natural Language Processing

Peratham Wiriyathammabhum, Douglas Summers-Stay, Cornelia Fermüller, Yiannis Aloimonos
2016 ACM Computing Surveys  
We also present a unified view for the field and propose possible future directions.  ...  We make an analog of distributional semantics in computer vision and natural language processing as image embedding and word embedding, respectively.  ...  Cynthia Matuszek for very useful advice and discussions. We thank Dr. Marco Baroni for providing a useful knowledge source.  ... 
doi:10.1145/3009906 fatcat:bdgaeoz4w5djhd5spab4lrc4au

Motion Prediction Under Multimodality with Conditional Stochastic Networks [article]

Katerina Fragkiadaki, Jonathan Huang, Alex Alemi, Sudheendra Vijayanarasimhan, Susanna Ricco, Rahul Sukthankar
2017 arXiv   pre-print
Training stochastic networks involves an intractable marginalization over stochastic variables.  ...  Given a visual history, multiple future outcomes for a video scene are equally probable, in other words, the distribution of future outcomes has multiple modes.  ...  For training, we pretrained the encoder for body joint detection in the same dataset, and then finetuned the whole model in the forecasting.  ... 
arXiv:1705.02082v1 fatcat:gihpo2x67nfczhntdrsehxar2y

Program

2021 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)  
, and deep neural network (DNN), for network intrusion detection.  ...  framework for embedded systems.  ... 
doi:10.1109/icce-tw52618.2021.9602919 fatcat:aetmvxb7hfah7iuucbamos2wgu

A critical evaluation of location based services and their potential

Jonathan Raper, Georg Gartner, Hassan Karimi, Chris Rizos
2007 Journal of Location Based Services  
The second question may be posed in several ways.  ...  The first question requires the use of position determination technology (PDT) that is either carried by the person initiating the query, e.g. a GPS receiver, or is accessed over a network connection,  ...  Acknowledgements The Editorial team of JLBS wish to thank the publishing team at Taylor and Francis for their support in establishing the Journal, the members of the Editorial Board who have reviewed this  ... 
doi:10.1080/17489720701584069 fatcat:spmkpyyds5bzfnmu7dgidrcpqq

A Survey of Augmented Reality Technologies, Applications and Limitations

D.W.F. Van Krevelen, R. Poelman
2010 International Journal of Virtual Reality  
Optical Promising approaches for 6DOF pose estimation of users and objects in general settings are vision-based.  ...  Complementary to RFID one can apply the wide-area IEEE 802.11b/g standards for both wireless networking and tracking as well.  ... 
doi:10.20870/ijvr.2010.9.2.2767 fatcat:cjyqi6agargo5ki2wftmgnd4nu
« Previous Showing results 1 — 15 out of 713 results