arXiv subjects

Minh Tran

Publications and source records attributed to Minh Tran.

59 records · Page 4Linked to original sources

arXiv2021

Multiple Meta-model Quantifying for Medical Visual Question Answering

Transfer learning is an important step to extract meaningful features and overcome the data limitation in the medical Visual Question Answering (VQA) task. However, most of the existing medical VQA methods rely on external data for transfer learning, while the meta-data within the dataset is not fully utilized. In this paper, we present a new multiple meta-model quantifying method that effectively learns meta-annotation and leverages meaningful features to the medical VQA task. Our proposed method is designed to increase meta-data by auto-annotation, deal with noisy labels, and output meta-models which provide robust features for medical VQA tasks. Extensively experimental results on two public medical VQA datasets show that our approach achieves superior accuracy in comparison with other state-of-the-art methods, while does not require external data to train meta-models.

cs.CV↗

arXiv2020

Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction

Offensive and abusive language is a pressing problem on social media platforms. In this work, we propose a method for transforming offensive comments, statements containing profanity or offensive language, into non-offensive ones. We design a RETRIEVE, GENERATE and EDIT unsupervised style transfer pipeline to redact the offensive comments in a word-restricted manner while maintaining a high level of fluency and preserving the content of the original text. We extensively evaluate our method's performance and compare it to previous style transfer models using both automatic metrics and human evaluations. Experimental results show that our method outperforms other models on human evaluations and is the only approach that consistently performs well on all automatic evaluation metrics.

cs.CL↗

arXiv2020

Robust Deep Learning Framework For Predicting Respiratory Anomalies and Diseases

This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods.

cs.SD↗

arXiv2020

Are you really looking at me? A Feature-Extraction Framework for Estimating Interpersonal Eye Gaze from Conventional Video

Despite a revolution in the pervasiveness of video cameras in our daily lives, one of the most meaningful forms of nonverbal affective communication, interpersonal eye gaze, i.e. eye gaze relative to a conversation partner, is not available from common video. We introduce the Interpersonal-Calibrating Eye-gaze Encoder (ICE), which automatically extracts interpersonal gaze from video recordings without specialized hardware and without prior knowledge of participant locations. Leveraging the intuition that individuals spend a large portion of a conversation looking at each other enables the ICE dynamic clustering algorithm to extract interpersonal gaze. We validate ICE in both video chat using an objective metric with an infrared gaze tracker (F1=0.846, N=8), as well as in face-to-face communication with expert-rated evaluations of eye contact (r= 0.37, N=170). We then use ICE to analyze behavior in two different, yet important affective communication domains: interrogation-based deception detection, and communication skill assessment in speed dating. We find that honest witnesses break interpersonal gaze contact and look down more often than deceptive witnesses when answering questions (p=0.004, d=0.79). In predicting expert communication skill ratings in speed dating videos, we demonstrate that interpersonal gaze alone has more predictive power than facial expressions.

cs.CV↗

arXiv2018

Vernier spectrometer using counter-propagating soliton microcombs

Acquisition of laser frequency with high resolution under continuous and abrupt tuning conditions is important for sensing, spectroscopy and communications. Here, a single microresonator provides rapid and broad-band measurement of frequencies across the optical C-band with a relative frequency precision comparable to conventional dual frequency comb systems. Dual-locked counter-propagating solitons having slightly different repetition rates are used to implement a Vernier spectrometer. Laser tuning rates as high as 10 THz/s, broadly step-tuned lasers, multi-line laser spectra and also molecular absorption lines are characterized using the device. Besides providing a considerable technical simplification through the dual-locked solitons and enhanced capability for measurement of arbitrarily tuned sources, this work reveals possibilities for chip-scale spectrometers that greatly exceed the performance of table-top grating and interferometer-based devices.

physics.optics↗