Filters








193 Hits in 7.2 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.  ...  Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the approaches using DNNs for multimodal audiovisual applications do not consider predictive uncertainty  ...  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.  ...  Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the approaches using DNNs for multimodal audiovisual applications do not consider predictive uncertainty  ...  Figure 1 : Uncertainty-aware audiovisual activity recognition art results.  ... 
doi:10.1109/iccv.2019.00640 dblp:conf/iccv/SubedarKLTH19 fatcat:pe7orp5eeff3tj4ltaij3ht4za

2020 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
., +, TASLP 2020 1356-1369 Online Speaker Adaptation Using Memory-Aware Networks for Speech Recognition.  ...  ., +, TASLP 2020 2598-2609 Online Speaker Adaptation Using Memory-Aware Networks for Speech Recognition.  ... 
doi:10.1109/taslp.2021.3055391 fatcat:7vmstynfqvaprgz6qy3ekinkt4

2020 Index IEEE Transactions on Cognitive and Developmental Systems Vol. 12

2020 IEEE Transactions on Cognitive and Developmental Systems  
., +, TCDS March 2020 30-42 Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially Aware Language Acquisition.  ...  Ramicic, M., +, TCDS March 2020 64-72 Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially Aware Language Acquisition.  ... 
doi:10.1109/tcds.2020.3044690 fatcat:yfo6c366aramfdltqegqyqphbq

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
This paper introduces an uncertainty-aware audiovisual fusion approach that quantifies modality-wise uncertainty towards emotion prediction.  ...  Our evaluation on two emotion recognition corpora, AVEC 2019 CES and IEMOCAP, shows that audiovisual emotion recognition can considerably benefit from well-calibrated and well-ranked latent uncertainty  ...  [41] applied Bayesian DNNs for uncertainty-aware audiovisual fusion to improve human activity recognition performance. Similarly, Tian et al.  ... 
arXiv:2206.05833v1 fatcat:7skw5owwpndkdgwrbmlymwwexu

Table of Contents

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Amar 1143 Temporarily-Aware Context Modeling Using Generative Adversarial Networks for Speech Activity Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . T.  ...  Spors 1016 Online Speaker Adaptation Using Memory-Aware Networks for Speech Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/taslp.2020.3046148 fatcat:hirdphjf6zeqdjzwnwlwlamtb4

Ensemble of Students Taught by Probabilistic Teachers to Improve Speech Emotion Recognition

Kusha Sridhar, Carlos Busso
2020 Interspeech 2020  
We use uncertainty modeling with Monte-Carlo (MC) dropout to create a distribution for the embeddings of an intermediate dense layer of the teacher.  ...  Reliable and generalizable speech emotion recognition (SER) systems have wide applications in various fields including healthcare, customer service, and security and defense.  ...  MC dropout is a technique to approximate Bayesian inference in deep neural networks (DNNs) using dropout regularization while training and testing the models.  ... 
doi:10.21437/interspeech.2020-2694 dblp:conf/interspeech/SridharB20 fatcat:c4jfkqmufjaqroepxrknx3eyjq

A Survey of Content-Aware Video Analysis for Sports

Huang-Chia Shih
2018 IEEE transactions on circuits and systems for video technology (Print)  
In each group, the gap between sensation and content excitement must be bridged using proper strategies. In this regard, a content-aware approach is required to determine user demands.  ...  Content-aware analysis methods are discussed with respect to object-, event-, and context-oriented groups.  ...  One of the most salient achievements is action and activity recognition through deep learning, which has been performed widely in recent years [94] , [96] .  ... 
doi:10.1109/tcsvt.2017.2655624 fatcat:rwqzu46sgfb7tpkcav4ysmh6ae

The Active Inference Approach to Ecological Perception: General Information Dynamics for Natural and Artificial Embodied Cognition

Adam Linson, Andy Clark, Subramanian Ramamoorthy, Karl Friston
2018 Frontiers in Robotics and AI  
In particular, the active inference framework (AIF) makes it possible to bridge connections from computational neuroscience and robotics/AI to ecological psychology and phenomenology, revealing common  ...  AIF opposes the mechanistic to the reductive, while staying fully grounded in a naturalistic and information-theoretic foundation, using the principle of free energy minimization.  ...  Representation in Cognitive Science: Enactivism, Ecological Psychology & Cybernetics, " held at the University of Sussex, organized by Jonny Lee, Joe Dewhurst, and Adrian Downey, and at "The World in Us  ... 
doi:10.3389/frobt.2018.00021 pmid:33500908 pmcid:PMC7805975 fatcat:revzkjlelvcdtpi2kifdnra2e4

A review of affective computing: From unimodal analysis to multimodal fusion

Soujanya Poria, Erik Cambria, Rajiv Bajpai, Amir Hussain
2017 Information Fusion  
In this paper, we focus mainly on the use of audio, visual and text information for multimodal affect analysis, since around 90% of the relevant literature appears to cover these three modalities.  ...  Various methods used under this category include: SVMs, Bayesian inference, Dempster-Shafer theory, dynamic bayesian networks, neural networks and maximum entropy models.  ...  The Bayesian inference fusion method fuses multimodal information based on rules of probability theory.  ... 
doi:10.1016/j.inffus.2017.02.003 fatcat:ytebhjxlz5bvxcdghg4wxbvr6a

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)  
V.; Alahari, Karteek 2804 Context Aware Group Activity Recognition DAY 3 -Jan 14, 2021 Hendri, Pirdiansyah; Hsieh, Jun- Wei; Yang,Chen, Ping 2809 Deep Real-time Hand Detection using CFPN on Embedded  ...  Novel Deep Architectures DAY 3 -Jan 14, 2021 Berg, Henrik; Hjelmervik, Karl Thomas 1801 Deep Learning on Active Sonar Data Using Bayesian Optimization for Hyperparameter Tuning DAY 3 -Jan 14  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

2020 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 31

2020 IEEE Transactions on Neural Networks and Learning Systems  
., +, TNNLS Dec. 2020 5041-5054 Image recognition A Semisupervised Recurrent Convolutional Attention Model for Human Activity Recognition.  ...  Chen, S., +, TNNLS Dec. 2020 5204-5218 Mixture models A Double-Variational Bayesian Framework in Random Fourier Features for Indefinite Kernels.  ...  + Check author entry for coauthors Fuzzy logic A Survey of Computational Intelligence Techniques for Wind Power Uncertainty Quantification in Smart Grids.  ... 
doi:10.1109/tnnls.2020.3045307 fatcat:34qoykdtarewhdscxqj5jvovqy

Table of contents

2021 ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Jianlong Tan, Institute of Information Engineering, Chinese Academy of Sciences, China MLSP-28.3: FAILURE PREDICTION BY CONFIDENCE ESTIMATION OF .................................................... 4085 UNCERTAINTY-AWARE  ...  INFERENCE APPROACH FOR LOCATION-BASED MICRO .................................. 2440 MOTIONS USING RADIO FREQUENCY SENSING David A.  ... 
doi:10.1109/icassp39728.2021.9414617 fatcat:m5ugnnuk7nacbd6jr6gv2lsfby

A comprehensive study of visual event computing

WeiQi Yan, Declan F. Kieran, Setareh Rafatirad, Ramesh Jain
2010 Multimedia tools and applications  
A probabilistic framework, based on Bayesian inference, is used to reason whether interesting events are presented.  ...  prior knowledge and data variation (HMM, Bayesian network, etc); 3) graph partitioning of the weight matrix.  ... 
doi:10.1007/s11042-010-0560-9 fatcat:ak6u3eefefgjhmbpr7asru3n7u

A Review of Human Activity Recognition Methods

Michalis Vrigkas, Christophoros Nikou, Ioannis A. Kakadiaris
2015 Frontiers in Robotics and AI  
In particular, we divide human activity classification methods into two large categories according to whether they use data from different modalities or not.  ...  Finally, we report the characteristics of future research directions and present some open issues on human activity recognition.  ...  Many works on human activity recognition based on deep learning techniques have been proposed in the literature.  ... 
doi:10.3389/frobt.2015.00028 fatcat:ywzq5ej2gbhatg62sp46t3usgi
« Previous Showing results 1 — 15 out of 193 results