Filters








38,934 Hits in 5.8 sec

A spatially-aware tangible interface for computer-aided design

Lee Chia-Hsun, Ma Yu-Pin, Jeng Taysheng
2003 CHI '03 extended abstracts on Human factors in computer systems - CHI '03  
This paper presents a Computer-Aided Design (CAD) platform for designers to navigate and construct 3D model intuitively through Tangible User Interfaces (TUIs).  ...  A semitransparent tablet as vertical display can be dynamically placed on the horizontal projected plane that triggers displaying spatially-contiguous 3D section images of the 3D CAD model.  ...  The vertical plane is a tablet consisting of a semi-transparent glass and a Light-Emitting Diode (LED) embedded.  ... 
doi:10.1145/766090.766094 fatcat:obbvyzncqzactpv6ox73ynugmy

A spatially-aware tangible interface for computer-aided design

Lee Chia-Hsun, Ma Yu-Pin, Jeng Taysheng
2003 CHI '03 extended abstracts on Human factors in computing systems - CHI '03  
This paper presents a Computer-Aided Design (CAD) platform for designers to navigate and construct 3D model intuitively through Tangible User Interfaces (TUIs).  ...  A semitransparent tablet as vertical display can be dynamically placed on the horizontal projected plane that triggers displaying spatially-contiguous 3D section images of the 3D CAD model.  ...  The vertical plane is a tablet consisting of a semi-transparent glass and a Light-Emitting Diode (LED) embedded.  ... 
doi:10.1145/765891.766094 dblp:conf/chi/Chia-HsunYT03 fatcat:epcdlzoj5zglre4rtycsn4ww5u

A survey on depth based 3D image Modeling

Dr. Dayanand G Savakar, Ravi Hosur
2017 International Journal of Engineering and Technology  
INTRODUCTION Depth based 3D-object construction and its recognition is the most challenging area of research in the DIP (Digital Image Processing).  ...  Herrera Carlos R, et al., (2015) ) proposes a method for constructing 3D using 2D by using a technique centroid clustering process by combining all the depth images in the cluster.  ...  Costa, et al., (2000) ) proposes a technique for 3D image recognition with a 2D intensity image with an edge comprising intensity based images pair constructed with a camera by relational indexing of new  ... 
doi:10.21817/ijet/2017/v9i4/170904117 fatcat:gnrrsxanajfsvlg67ptjgwhwn4

Challenging Black Box Technology Power Imbalances by Exposing Them: "Persuasive System" as a Prism for Decomposing Contemporary Surveillance

Philip Di Salvo, Salvatore Vitale
2021 Surveillance & Society  
This article contributes to the discussion around surveillance invisibility by engaging with the existing literature and discussing Salvatore Vitale's "Persuasive System" installation as a case study.  ...  surveillance as a "black box," the article frames power imbalances involved in biometrics and video surveillance technologies and shows how Vitale's installation aims at playing with and exposing these dynamics by  ...  Images captured by the cameras were made visible in real time on a screen at the installation site.  ... 
doi:10.24908/ss.v19i4.15117 fatcat:2ibijbcwpjekfd6rg26sbystja

Clustering and Recognition of Spatiotemporal Features through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks [article]

Kun Su, Eli Shlizerman
2020 arXiv   pre-print
In this study, we propose an embedding approach to visualize and interpret the representation of data by these models.  ...  In particular, we demonstrate that embedding space projections of the decoder states of RNN Seq2Seq model trained on sequences prediction are organized in clusters capturing similarities and differences  ...  We construct synthetic data examples to demonstrate the construction of the interpretable embedding space.  ... 
arXiv:1905.12176v2 fatcat:p3fo345x6zbrbiabikdgzkedc4

Clustering and Recognition of Spatiotemporal Features Through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks

Kun Su, Eli Shlizerman
2020 Frontiers in Artificial Intelligence  
In this study, we propose an embedding approach to visualize and interpret the representation of data by these models.  ...  In particular, we demonstrate that embedding space projections of the decoder states of RNN Seq2Seq model trained on sequences prediction are organized in clusters capturing similarities and differences  ...  The authors would also like to acknowledge the partial support by the Departments of Applied Mathematics, Electrical & Computer Engineering, the Center of Computational Neuroscience (CNC), and the eScience  ... 
doi:10.3389/frai.2020.00070 pmid:33733187 pmcid:PMC7861310 fatcat:ebgk4kicwvftvcclevffxyxia4

Concept Mapping

Jessie Wilson, Angie Mandich, Lilian Magalhães
2015 Qualitative Health Research  
It allows researchers to provide a transparent methodological account of the co-construction of knowledge during the research process and deepens their understanding of how they collect, select and interpret  ...  It is a position that is centrally located between excessive distance (withdrawn from the image) and insufficient distance: being so close to the image that the audience interprets it as a part of reality  ... 
doi:10.1177/1049732315616623 pmid:26631678 fatcat:t2dwbvuk4rhu7ikbaabpo4nkza

Explainable Machine Learning for Scientific Insights and Discoveries

Ribana Roscher, Bastian Bohn, Marco F. Duarte, Jochen Garcke
2020 IEEE Access  
INDEX TERMS Explainable machine learning, informed machine learning, interpretability, scientific consistency, transparency. 42200 This work is licensed under a Creative Commons Attribution 4.0 License  ...  In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability  ...  The construction of Phys-Net is made design-transparent in the sense that the network is constructed to capture the arrangement of blocks by using alternating upsampling and convolution layers, and an  ... 
doi:10.1109/access.2020.2976199 fatcat:7wk6ljxlqrdwhpbv7xjk75buk4

Towards Interpretable Deep Metric Learning with Structural Matching [article]

Wenliang Zhao, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie Zhou
2021 arXiv   pre-print
In this paper, we present a deep interpretable metric learning (DIML) method for more transparent embedding learning.  ...  However, most existing deep metric learning methods match the images by comparing feature vectors, which ignores the spatial structure of images and thus lacks interpretability.  ...  Acknowledgements This work was supported in part by the National Natural Science Foundation of China under Grant 61822603, Grant U1813218, and Grant U1713214, in part by a grant from the Beijing Academy  ... 
arXiv:2108.05889v1 fatcat:ffcrncpgkzgevieggt5ixdt22e

Explainable Machine Learning for Scientific Insights and Discoveries [article]

Ribana Roscher, Bastian Bohn, Marco F. Duarte, Jochen Garcke
2019 arXiv   pre-print
In this article we review explainable machine learning in view of applications in the natural sciences and discuss three core elements which we identified as relevant in this context: transparency, interpretability  ...  Here, domain knowledge led to the constructions of a network architecture that embedded invariance using a higher-order multiplicative layer.  ...  Attention modules in recurrent NNs for multi-modal sensor-based activity recognition have been used by .  ... 
arXiv:1905.08883v2 fatcat:bwbkmljfljcpboqmppoemari64

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

Aishwarya Agrawal, Dhruv Batra, Devi Parikh, Aniruddha Kembhavi
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Finally, GVQA is more transparent and interpretable than existing VQA models.  ...  Specifically, GVQA explicitly disentangles the recognition of visual concepts present in the image from the identification of plausible answer space for a given question, enabling the model to more robustly  ...  This work was funded in part by: NSF CA-REER awards, ONR YIP awards, Google FRAs, Amazon ARAs, DARPA XAI, and ONR Grants N00014-14-1-{0679, 2713} to DB, DP, and PGA Family Foundation award to DP.  ... 
doi:10.1109/cvpr.2018.00522 dblp:conf/cvpr/AgrawalBPK18 fatcat:yobbk32dybfwhiexfwcwjbmvem

Ubiquitous Talker: Spoken Language Interaction with Real World Objects [article]

Katashi Nagao, Jun Rekimoto
1995 arXiv   pre-print
A crucial issue within this area, is the recognition of real world objects or situations.  ...  Augmented reality is a research area that tries to embody an electronic information space within the real world, through computational devices.  ...  Special thanks go to researchers in Speech Technology Group at Electrotechnical Laboratory for their help to develop the speech recognition module.  ... 
arXiv:cmp-lg/9505038v1 fatcat:j3zmfkmqlbh7baqov2xulcobqe

A database-based framework for gesture recognition

Vassilis Athitsos, Haijing Wang, Alexandra Stefan
2010 Personal and Ubiquitous Computing  
This database-based approach is applied to two gesture recognition problems: handshape categorization and motion-based recognition of American Sign Language (ASL) signs.  ...  The large variability in appearance among different examples of the same gesture is addressed by creating large gesture databases, that store enough exemplars from each gesture to capture the variability  ...  Acknowledgements This work has been supported by National Science Foundation grants IIS-0705749 and IIS-0812601, as well as by a University of Texas at Arlington startup grant to Professor Athitsos, and  ... 
doi:10.1007/s00779-009-0276-x fatcat:foxzq7xksbeldls4jm6pq6ytzq

The listening room

Alexa Wright, Alun Evans, Alf Linney, Mike Lincoln
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
To give context to the ideas behind The Listening Room we will describe the work with reference to two previous interactive works by the authors -Face Value (2000) and Alter Ego (2005) .  ...  by the user which are recognised by a speech recognition system.  ...  were constructed ( Figure 5 ).  ... 
doi:10.1145/1291233.1291391 dblp:conf/mm/WrightELL07 fatcat:tlxn5pzqyre5zkihjypbjgokhq

Deep Learning, Natural Language Processing, and Explainable Artificial Intelligence in the Biomedical Domain [article]

Milad Moradi, Matthias Samwald
2022 arXiv   pre-print
A word-based vector space model is usually constructed based on the normalized frequencies of co-occurring words in a corpus (Camacho-Collados and Pilehvar, 2018).  ...  (Guidotti et al., 2018) define the model-based interpretability as 'transparent-box design' that refers to directly designing a transparent model with the goal of solving the same problem that can be  ... 
arXiv:2202.12678v2 fatcat:4nv42mbpuveb7euxkr4b6ojuxi
« Previous Showing results 1 — 15 out of 38,934 results