Filters








1,670 Hits in 4.4 sec

Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference [article]

Mahesh Subedar, Ranganath Krishnan, Paulo Lopez Meyer, Omesh Tickoo, Jonathan Huang
2019 arXiv   pre-print
Our contribution in this work is to propose an uncertainty aware multimodal Bayesian fusion framework for activity recognition.  ...  Monte Carlo dropout (MC dropout) approximate Bayesian inference.  ...  Figure 1 : Uncertainty-aware audiovisual activity recognition art results.  ... 
arXiv:1811.10811v3 fatcat:bv2mnlhpqregdcac4n3buf7imq

Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational Inference

Mahesh Subedar, Ranganath Krishnan, Paulo Lopez Meyer, Omesh Tickoo, Jonathan Huang
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Our contribution in this work is to propose an uncertainty aware multimodal Bayesian fusion framework for activity recognition.  ...  Monte Carlo dropout (MC dropout) approximate Bayesian inference.  ...  Figure 1 : Uncertainty-aware audiovisual activity recognition art results.  ... 
doi:10.1109/iccv.2019.00640 dblp:conf/iccv/SubedarKLTH19 fatcat:pe7orp5eeff3tj4ltaij3ht4za

Robust Location-Aware Activity Recognition Using Wireless Sensor Network in an Attentive Home

Ching-Hu Lu, Li-Chen Fu
2009 IEEE Transactions on Automation Science and Engineering  
activities by utilizing a generalized and enhanced Bayesian Network fusion engine with inputs from a set of the most informative features.  ...  With observations from a variety of multimodal and unobtrusive wireless sensors seamlessly integrated into ambient-intelligence compliant objects (AICOs), the approach infers a single resident's interleaved  ...  of location-aware activity recognition.  ... 
doi:10.1109/tase.2009.2021981 fatcat:yzqulckdoferbjdssri2cgd3km

Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia [article]

Utkarsh Sarawgi, Wazeer Zulfikar, Rishab Khincha, Pattie Maes
2020 arXiv   pre-print
In this work, we propose an uncertainty-aware boosting technique for multi-modal ensembling to predict Alzheimer's Dementia Severity.  ...  This work aims to encourage fair and aware models. The source code is available at https://github.com/wazeerzulfikar/alzheimers-dementia  ...  We propose an uncertainty-aware ensembling technique for a multimodal system where each of the base learners correspond to the different modalities.  ... 
arXiv:2010.01440v2 fatcat:v4utmvmhv5g3rje3lh3xbggna4

Fusion Considerations in Monitoring and Handling Agitation Behaviour for Persons with Dementia

Victor Siang Fook, Qiang Qiu, Jit Biswas, Aung Phyo Wai
2006 2006 9th International Conference on Information Fusion  
In particular, we present the subtle design and implementation of a fusion architecture for monitoring and handling agitation behaviour for persons with dementia.  ...  Bayesian Inference 88 % Table 3 : 3 Experimental Results on UDM Agitation in Bed Recognition Rate Reducing with inappropriate Sensor Modality selected through Bayesian Inference shown inFigure  ...  networks to deal with uncertainty and improve recognition rate for UDM in chair and bed respectively.  ... 
doi:10.1109/icif.2006.301588 dblp:conf/fusion/FookQBW06 fatcat:qyg3w43wgrawpnkd2ipgpstyve

2018 Index IEEE Transactions on Affective Computing Vol. 9

2019 IEEE Transactions on Affective Computing  
., þ, T-AFFC July -Sept. 2018 351-361 Multimodal First Impression Analysis with Deep Residual Networks.  ...  -Dec. 2018 491-506 Predictive models Multimodal First Impression Analysis with Deep Residual Networks.  ... 
doi:10.1109/taffc.2019.2905448 fatcat:4a5hvv4bkneq5d6eilv6tcn37u

Conversation as Action Under Uncertainty [article]

Tim Paek, Eric J. Horvitz
2013 arXiv   pre-print
Treating conversation as inference and decision making under uncertainty, we propose a task independent, multimodal architecture for supporting robust continuous spoken dialog called Quartet.  ...  We introduce four interdependent levels of analysis, and describe representations, inference procedures, and decision strategies for managing uncertainties within and between the levels.  ...  , inference procedures, and decision strategies for designing spoken dialog systems with the ability to manage uncertainties through grounding.  ... 
arXiv:1301.3883v1 fatcat:qyndl4whlfdhhdl3osunb7veai

Low-level grounding in a multimodal mobile service robot conversational system using graphical models

Plamen Prodanov, Andrzej Drygajlo, Jonas Richiardi, Anil Alexander
2007 Intelligent Service Robotics  
with multimodal grounding.  ...  The Bayesian networks used in the grounding model are specially designed for modularity and computationally efficient inference.  ...  The uncertainties in the four-level grounding state inference (channel, signal, intention and conversation) are modeled using Bayesian networks.  ... 
doi:10.1007/s11370-006-0001-9 fatcat:rtcnjs5einexzgitzmph6ch32q

Context-aware decision making under uncertainty for voice-based control of smart home

Pedro Chahuara, François Portet, Michel Vacher
2017 Expert systems with applications  
This framework for building context aware systems uses a hierarchical knowledge model so that different inference modules can communicate and reason with same concepts and relations.  ...  Although some expert systems are able to deal with uncertainty, the Markov Logic Network approach brings a unified theory for dealing with logical entailment, uncertainty and missing data.  ...  0 13 0 Table 4 : 4 Correct decision rate with and without activity uncertainty -with the multimodal SWEET-HOME dataset Situation MLN without MLN with /Expected Utility uncertainty uncertainty  ... 
doi:10.1016/j.eswa.2017.01.014 fatcat:u5beskkwv5ggbodrztnesczpim

An adaptive evidence structure for Bayesian recognition of 3D objects

Ahmed M. Naguib, Sukhan Lee
2015 Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication - IMCOM '15  
We separate feature space into binary TRUE/FALSE regions which allows us to drive Bayesian inference prior conditional probabilities from statistical database.  ...  In this work, we show problems of using simple Naïve Bayesian classifier and propose a Tree-Augmented Naïve (TAN) Bayesian Networkbased classifier.  ...  Non-target object / dark condition: decision becomes 25% with 48% uncertainty. Target object / normal light: decision is 92% with 0.1% uncertainty.  ... 
doi:10.1145/2701126.2701160 dblp:conf/icuimc/NaguibL14 fatcat:ewbhznhkpzhilccy63q2ll3t3m

Graphical models for social behavior modeling in face-to face interaction

Alaeddine Mihoub, Gérard Bailly, Christian Wolf, Frédéric Elisei
2016 Pattern Recognition Letters  
For this end, we present a multimodal behavioral model based on a Dynamic Bayesian Network (DBN).  ...  The model was inferred from multimodal data of interacting dyads in a specific scenario designed to foster mutual attention and multimodal deixis of objects and places in a collaborative task.  ...  These joint multimodal scores are used to infer a coverbal behavioral model for the instructor.  ... 
doi:10.1016/j.patrec.2016.02.005 fatcat:267o5jnx3vd6fjcnf6ynsjb3sq

Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks

Young-Seol Lee, Sung-Bae Cho
2012 Pattern Analysis and Applications  
Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources.  ...  The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems.  ...  Bayesian network [17] (one of recognition methods introduced in Sect. 2) with it.  ... 
doi:10.1007/s10044-012-0300-z fatcat:zxfpuulnjjdkjmayumprvpxrf4

A Bayesian framework for active artificial perception

J. F. Ferreira, J. Lobo, P. Bessiere, M. Castelo-Branco, J. Dias
2013 IEEE Transactions on Cybernetics  
In this text, we present a Bayesian framework for active multimodal perception of 3D structure and motion.  ...  Moreover, interaction and navigation requires maximal awareness of spatial surroundings, which in turn is obtained through active attentional and behavioural exploration of the environment.  ...  ACTIVE EXPLORATION USING BAYESIAN MODELS FOR MULTIMODAL PERCEPTION A.  ... 
doi:10.1109/tsmcb.2012.2214477 pmid:23014760 fatcat:2och4qlnavbd3f6pyy4obyne3a

Multimodal affect recognition in learning environments

Ashish Kapoor, Rosalind W. Picard
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
The multimodal sensory information from facial expressions and postural shifts of the learner is combined with information about the learner's activity on the computer.  ...  We propose a multi-sensor affect recognition system and evaluate it on the challenging task of classifying interest (or disinterest) in children trying to solve an educational puzzle on the computer.  ...  Acknowledgments Thanks to Selene Mota for help with the data collection. This research was supported by NSF ITR grant 0325428. REFERENCES  ... 
doi:10.1145/1101149.1101300 dblp:conf/mm/KapoorP05 fatcat:macmj3nw4nfx5ggpjt6wwibfdu

COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition [article]

Mani Kumar Tellamekala, Shahin Amiriparian, Björn W. Schuller, Elisabeth André, Timo Giesbrecht, Michel Valstar
2022 arXiv   pre-print
In both classification and regression settings, we compare our uncertainty-aware fusion model with standard model-agnostic fusion baselines.  ...  This paper introduces an uncertainty-aware audiovisual fusion approach that quantifies modality-wise uncertainty towards emotion prediction.  ...  [41] applied Bayesian DNNs for uncertainty-aware audiovisual fusion to improve human activity recognition performance. Similarly, Tian et al.  ... 
arXiv:2206.05833v1 fatcat:7skw5owwpndkdgwrbmlymwwexu
« Previous Showing results 1 — 15 out of 1,670 results