Search Results for author:
Found 8 papers, 7 papers with code
LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks.
Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment
Self-supervised learning provides an opportunity to explore unlabeled chest X-rays and their associated free-text reports accumulated in clinical routine without manual supervision.
Soft-Attention Improves Skin Cancer Classification Performance
Soft-Attention mechanism enables a neural network toachieve this goal.
Ranked #1 on
Lesion Classification
on ISIC 2017
Self-Supervised Claim Identification for Automated Fact Checking
We propose a novel, attention-based self-supervised approach to identify "claim-worthy" sentences in a fake news article, an important first step in automated fact-checking.
Ranked #1 on
Fact Checking
on CDCD
Attention based Writer Independent Handwriting Verification
The task of writer verification is to provide a likelihood score for whether the queried and known handwritten image samples belong to the same writer or not.
Ranked #1 on
Handwriting Verification
on AND Dataset
Ultra Efficient Transfer Learning with Meta Update for Cross Subject EEG Classification
The pattern of Electroencephalogram (EEG) signal differs significantly across different subjects, and poses challenge for EEG classifiers in terms of 1) effectively adapting a learned classifier onto a new subject, 2) retaining knowledge of known subjects after the adaptation.
Explanation based Handwriting Verification
The dataset is released for publicuse and the methods can be extended to provide explanations on other verification taskslike face verification and bio-medical comparison.
Explainable Artificial Intelligence (XAI)
Face Verification
+1
Hybrid Feature Learning for Handwriting Verification
Experiments are performed by complementing one of the HEF methods with one ALF method on 150000 pairs of samples of the word "AND" cropped from handwritten notes written by 1500 writers.
