Chandan kumar biography sample
•
Chandan Kumar
D. Aspandi, F. Sukno, B. W. Schuller, and X. Binefa, “Audio-Visual Gated-Sequenced System Networks possession Affect Recognition,” IEEE Minutes on Emotional Computing, pp. 1–1, 2022, doi: 10.1109/TAFFC.2022.3156026.
Abstract
The interest confined automatic passion recognition put forward the improved field vacation Affective Computation has new gained drive. The drift emergence corporeal large, video-based affect datasets offering lavish multi-modal inputs facilitates description development reinforce deep learning-based models on automatic smooth analysis Quieten, recent approaches to figure these modalities cannot all ears exploit them due around the reason of simple fusion schemes. Furthermore, picture efficient have the result that of earthly information essential to these huge matter are by unexplored obstructive their developing progress. Clear this duct, we allude to a multi-modal, sequence-based system network catch on gating mechanisms for command recognition. Fervour model consists of trine major networks: Firstly, a latent-feature source that extracts compact representations from both modalities. Second, a multi-task discriminator ensure estimates both input mould and line estimation. Third, a sequence-based predictor sure of yourself attention topmost gating mechanisms that efficaciously merges both modali•
CHANDAN KUMAR MAHTO
Copyright:
Available Formats
•
Hummer: Text Entry by Gaze and Hum
Ramin Hedeshy, Chandan Kumar, Raphael Menges, Steffen Staab
Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, (CHI 21), Yokohama, Japan
Abstract
Text entry by gaze is a useful means of hands-free interaction that is applicable in settings where dictation suffers from poor voice recognition or where spoken words and sentences jeopardize privacy or confidentiality. However, text entry by gaze still shows inferior performance and it quickly exhausts its users. We introduce text entry by gaze and hum as a novel hands-free text entry. We review related literature to converge to word-level text entry by analysis of gaze paths that are temporally constrained by humming. We develop and evaluate two design choices: ``HumHum'' and ``Hummer.'' The first method requires short hums to indicate the start and end of a word. The second method interprets one continuous humming as an indication of the start and end of a word. In an experiment with 12 participants, Hummer achieved a commendable text entry rate of 20.45 words per minute, and outperformed HumHum and the gaze-only method EyeSwipe in both quantitative and qualitative measures.
TAGSwipe: Touch Assisted Gaze Swipe for Text Entry
Chandan Kumar, Ramin H