Filters








1,081 Hits in 9.7 sec

Distance metric learning from uncertain side information for automated photo tagging

Lei Wu, Steven C.H. Hoi, Rong Jin, Jianke Zhu, Nenghai Yu
2011 ACM Transactions on Intelligent Systems and Technology  
To address the challenge of semantic gap, we propose a novel probabilistic distance metric learning scheme that (1) automatically derives constraints from the uncertain side information, and (2) efficiently  ...  learns a distance metric from the derived constraints.  ...  To this end, this paper presents a novel probabilistic distance metric learning (PDML) framework, which aims to learn effective metrics from uncertain side information with application to automated photo  ... 
doi:10.1145/1899412.1899417 fatcat:krly2vmz65cvtkpuobw73frv4a

Distance metric learning from uncertain side information with application to automated photo tagging

Lei Wu, Steven C.H. Hoi, Rong Jin, Jianke Zhu, Nenghai Yu
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
To address the challenge of semantic gap, we propose a novel probabilistic distance metric learning scheme that (1) automatically derives constraints from the uncertain side information, and (2) efficiently  ...  learns a distance metric from the derived constraints.  ...  To this end, this paper presents a novel probabilistic distance metric learning (PDML) framework, which aims to learn effective metrics from uncertain side information with application to automated photo  ... 
doi:10.1145/1631272.1631293 dblp:conf/mm/WuHJZY09 fatcat:jfiaje3m7vfvjnayfy7bbi3se4

AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild

Ali Mollahosseini, Behzad Hasani, Mohammad H. Mahoor
2017 IEEE Transactions on Affective Computing  
Various evaluation metrics show that our deep neural network baselines can perform better than conventional machine learning methods and off-the-shelf facial expression recognition systems.  ...  Automated affective computing in the wild setting is a challenging problem in computer vision.  ...  If the annotators were uncertain about any of the facial expressions, images were tagged as uncertain.  ... 
doi:10.1109/taffc.2017.2740923 fatcat:iychfrtx3narvbaqyn6wjrmnn4

A Citizen Science Unmanned Aerial System Data Acquisition Protocol and Deep Learning Techniques for the Automatic Detection and Mapping of Marine Litter Concentrations in the Coastal Zone

Apostolos Papakonstantinou, Marios Batsaris, Spyros Spondylidis, Konstantinos Topouzelis
2021 Drones  
ML density maps were created using the automated classification results.  ...  In this context, we proposed a citizen science UAS data acquisition and annotation protocol combined with deep learning techniques for the automatic detection and mapping of ML concentrations in the coastal  ...  Additionally, tiles for which their class was uncertain and tagged as "not sure" from the annotation process were revised and placed in the appropriate class.  ... 
doi:10.3390/drones5010006 fatcat:sr6arirrabflloyn7w2xa6adv4

Automatic adaptation of open educational resources: an approach from a multilevel methodology based on students' preferences, educational special needs, artificial intelligence, and accessibility metadata

Paola Ingavelez-Guerra, Vladimir Robles-Bykbaev, Angel Perez-Munoz, Jose R. Hilera, Salvador Oton-Tortosa
2022 IEEE Access  
The need for adaptive e-learning environments that respond to learning variability is now a fundamental requirement in education, as it helps to ensure that students learn and pass their courses within  ...  The research conducted aims to contribute with an automated support tool in the generation of accessible educational resources that are correctly labeled for search and reuse.  ...  cannot be held responsible for any use which may be made of the information contained therein.  ... 
doi:10.1109/access.2021.3139537 fatcat:yzvcfil3hzbkjpu5emepo2mtsu

Content-based visual search learned from social media

Xirong Li
2012 ACM SIGMultimedia Records  
It is my pleasure to work in the ISIS group: Michael, Ivo, and Jan as my ping pong mates for years, Victoria, Vladimir, Dung, and Stratios for sharing offices, Cor, Jan-Mark, and Theo for interesting discussions  ...  , Gosia and Hamdi for the ISIS dinners, Daan and Bouke for sharing conference hotels, and our secretary Virginie who helped me much in the past years.  ...  [77] propose a semi-automatic method, by first learning a generic model for each tag using images from a professional photo forum.  ... 
doi:10.1145/2206765.2206774 fatcat:kxk6kciwhfe2hcqw546ez2coku

Designing for effective end-user interaction with machine learning

Saleema Amershi
2011 Proceedings of the 24th annual ACM symposium adjunct on User interface software and technology - UIST '11 Adjunct  
Together, these contributions can move us beyond ad-hoc designs for specific applications and provide a foundation for future researchers and developers of end-user interactive machine learning systems  ...  Designing for Effective End-User Interaction with Machine Learning Saleema Amershi Chair of the Supervisory Committee: Associate Professor James A.  ...  I also want to thank my bonus advisor, Desney Tan, for his unwavering encouragement. His insight and drive continues to inspire me.  ... 
doi:10.1145/2046396.2046416 dblp:conf/uist/Amershi11 fatcat:q3ticzzymngu5i7uhdcyshmt34

Learning Structure and Schemas from Heterogeneous Domains in Networked Systems: A Survey

Marenglen Biba, Fatos Xhafa
2010 2010 International Conference on Intelligent Networking and Collaborative Systems  
This paper presents a survey of the state-of-the-art methods for inferring structure from documents and schemas in networked environments.  ...  for which we analyze the recent developments on dealing with unstructured data in such domains.  ...  ACKNOWLEDGMENT The authors would like to thank the Braingain program of the Albanian Government for the support.  ... 
doi:10.1109/incos.2010.63 dblp:conf/incos/BibaX10 fatcat:2pbt6ci45fdclopif23djiehpe

Automatic Face Understanding: Recognizing Families in Photos [article]

Joseph P Robinson
2021 arXiv   pre-print
We built the largest database for kinship recognition. The data were labeled using a novel clustering algorithm that used label proposals as side information to guide more accurate clusters.  ...  The locations of landmarks are determined from generated heatmaps from which predicted landmark locations get penalized without accounting for the spread: a high scatter corresponds to low confidence and  ...  from the side of the mother, determine the mother), and practical use-cases (e.g., automate family photo-album creation).  ... 
arXiv:2102.08941v1 fatcat:eqje3jh23nb6do7crz7rw6342a

Application of Google Analytics Model for Evaluating the Visibility of Library Web Portals of the Uva Wellassa University, Sri Lanka

T. Pratheepan, M. Jayakananthan
2021 Asian Journal of Information Science and Technology  
Google Analytics is the most prevalent page tagging technique to evaluate the visibility of web portals.  ...  A user can choose his/her own dimensions and metrics from the menu at the left side of the window.  ...  If you ask for dimensions or metrics from two different groups, your options are limited to select from the same metrics and dimensions in the intersection of the two groups.  ... 
doi:10.51983/ajist-2021.11.1.2656 fatcat:hftzhv6rnjb3djrwvxszykohd4

Adversarial Edge-aware Image Colorization with Semantic Segmentation

Guangqian Kong, Huan Tian, Xun Duan, Huiyun Long
2021 IEEE Access  
However, previous methods often encounter problems with edge color leakage and difficulties in obtaining a plausible color output from the Euclidean distance.  ...  For more information, see https://creativecommons.org/licenses/by/4.0/ VOLUME 9, 2021  ...  ACKNOWLEDGMENT The authors would like to thank the Editor-in-Chief, an Associate Editor, and reviewers for their insightful comments and suggestions.  ... 
doi:10.1109/access.2021.3056144 fatcat:23kwdkfmovfzrm6mjocvb32tke

MARVEL - D3.1: Multimodal and privacy-aware audio-visual intelligence – initial version

Alexandros Iosifidis
2022 Zenodo  
as methodologies for improving the training and efficiency of AI models under supervised, unsupervised, and cross-modal contrastive learning settings.  ...  These include methods for Sound Event De- tection, Sound Event Localisation and Detection, Automated Audio Captioning, Visual Anomaly Detection, Visual Crowd Counting, Audio-Visual Crowd Counting, as well  ...  Part of the needed computations was implemented on a GPU donated from NVIDIA to K. Drossos.  ... 
doi:10.5281/zenodo.6821317 fatcat:eia7rkk5lfbg7khs3qcat5qd3m

I am Robot: (Deep) Learning to Break Semantic Image CAPTCHAs

Suphannee Sivakorn, Iasonas Polakis, Angelos D. Keromytis
2016 2016 IEEE European Symposium on Security and Privacy (EuroS&P)  
Since their inception, captchas have been widely used for preventing fraudsters from performing illicit actions.  ...  Subsequently, we design a novel low-cost attack that leverages deep learning technologies for the semantic annotation of images.  ...  Acknowledgements We would like to thank the anonymous reviewers, as well as Fabian Monrose and Michalis Polychronakis for their comments on previous drafts of this paper.  ... 
doi:10.1109/eurosp.2016.37 dblp:conf/eurosp/SivakornPK16 fatcat:u2gegsjtfnd3beflnxrem6idja

A Survey of Privacy Vulnerabilities of Mobile Device Sensors [article]

Paula Delgado-Santos, Giuseppe Stragapede, Ruben Tolosana, Richard Guest, Farzin Deravi, Ruben Vera-Rodriguez
2021 arXiv   pre-print
In addition, we review popular metrics in the literature to quantify the degree of privacy, and discuss powerful privacy methods to protect the sensitive data while preserving data utility for analysis  ...  Finally, open research questions a represented for further advancements in the field.  ...  For instance, in [131] the authors showed how demographic information can be inferred from geo-tagged photos on social networks.  ... 
arXiv:2106.10154v1 fatcat:voocjeorsvarznsgsjedkqgk5q

A Graphical Pronoun Analysis Tool for the PROTEST Pronoun Evaluation Test Suite

Christian Hardmeier, Liane Guillou
2016 European Association for Machine Translation Conferences/Workshops  
We present a graphical pronoun analysis tool and a set of guidelines for manual evaluation to be used with the PROTEST pronoun test suite for machine translation (MT).  ...  The tool provides a means for researchers to evaluate the performance of their MT systems and browse individual pronoun translations.  ...  Acknowledgements We would like to thank Marie Dubremetz and Miryam de Lhoneux for manually annotating the output of the DiscoMT 2015 systems.  ... 
dblp:conf/eamt/HardmeierG16 fatcat:ietwpniy6jhwvel3xxlxn5huqi
« Previous Showing results 1 — 15 out of 1,081 results