Dynamic Active Learning Based on Agreement and Applied to Emotion
Recognition in Spoken Interactions
Poster Session
/
Zhang, Yue
/
Coutinho, Eduardo
/
Zhang, Zixing
/
Quan, Caijiao
/
Schuller, Bjoern
Proceedings of the 2015 International Conference on Multimodal Interaction
2015-11-09
p.275-278
© Copyright 2015 ACM
Summary: In this contribution, we propose a novel method for Active Learning (AL) --
Dynamic Active Learning (DAL) -- which targets the reduction of the costly
human labelling work necessary for modelling subjective tasks such as emotion
recognition in spoken interactions. The method implements an adaptive query
strategy that minimises the amount of human labelling work by deciding for each
instance whether it should automatically be labelled by machine or manually by
human, as well as how many human annotators are required. Extensive experiments
on standardised test-beds show that DAL significantly improves the efficiency
of conventional AL. In particular, DAL achieves the same classification
accuracy obtained with AL with up to 79.17% less human annotation effort.
Enhancing 2D scatter plot visualization of multivariate data with haptic
effects
Short papers: information visualization
/
Coutinho, Edson A. G.
/
Santos, Selan R. dos
Proceedings of the 2013 Brazilian Symposium on Human Factors in Computing
Systems
2013-10-08
p.256-259
© Copyright 2013 SBC
Summary: This paper presents an ongoing proposal to enhance traditional multivariate
data visualization by adding haptic representation for the data. By combining
visual and haptic stimuli one may alleviate the information overload typically
found in situations where a large number of variables are mapped to the visual
channel alone. In this paper we report the results of a user study in which we
compared five haptic effects -- magnetism, stiffness, stickiness, viscosity,
and vibration -- in an attempt to classify them in terms of perceivability. By
perceivability we mean the degree of success in correctly detecting differences
of stimulus intensity, given a pairwise stimuli of the same haptic effect. The
results showed that magnetism and stiffness presented the worse results, while
vibration, stickiness, and viscosity, in that order, were best perceived by the
participants.
