Search Results for author:
Found 16 papers, 5 papers with code
SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix
This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update in large-scale stochastic optimization of machine learning models.
Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image Data
It implements an interpretability technique to analyze the contribution of textual and visual features during the generation of uncontrolled and controlled feedback.
DeepMediX: A Deep Learning-Driven Resource-Efficient Medical Diagnosis Across the Spectrum
In the rapidly evolving landscape of medical imaging diagnostics, achieving high accuracy while preserving computational efficiency remains a formidable challenge.
Vision Through the Veil: Differential Privacy in Federated Learning for Medical Image Classification
The proliferation of deep learning applications in healthcare calls for data aggregation across various institutions, a practice often associated with significant privacy concerns.
See Through the Fog: Curriculum Learning with Progressive Occlusion in Medical Imaging
In this paper, we propose a novel curriculum learning-based approach to train deep learning models to handle occluded medical images effectively.
Transcending Grids: Point Clouds and Surface Representations Powering Neurological Processing
In healthcare, accurately classifying medical images is vital, but conventional methods often hinge on medical data with a consistent grid structure, which may restrict their overall performance.
Interpretable Multimodal Emotion Recognition using Hybrid Fusion of Speech and Image Data
A new interpretability technique has been developed to identify the important speech & image features leading to the prediction of particular emotion classes.
Hybrid Fusion Based Interpretable Multimodal Emotion Recognition with Limited Labelled Data
This paper proposes a multimodal emotion recognition system, VIsual Spoken Textual Additive Net (VISTA Net), to classify emotions reflected by multimodal input containing image, speech, and text into discrete classes.
Affective Feedback Synthesis Towards Multimodal Text and Image Data
A feedback synthesis system has been proposed and trained using ground-truth human comments along with image-text input.
Region extraction based approach for cigarette usage classification using deep learning
This paper has proposed a novel approach to classify the subjects' smoking behavior by extracting relevant regions from a given image using deep learning.
Domain Adaptation based Interpretable Image Emotion Recognition using Facial Expression Recognition
It addresses the challenge of the insufficient availability of pre-trained models and well-annotated datasets for image emotion recognition (IER).
Computational Models for Academic Performance Estimation
Evaluation of students' performance for the completion of courses has been a major problem for both students and faculties during the work-from-home period in this COVID pandemic situation.
Video Skimming: Taxonomy and Comprehensive Survey
Video skimming, also known as dynamic video summarization, generates a temporally abridged version of a given video.
Attentive Recurrent Tensor Model for Community Question Answering
Further, we use the tensor parameters to introduce a 3-way interaction between question, answer and external features in vector space.
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
We present a novel idea that combines the neural, statistical and external features to provide an efficient solution to this problem.
Ranked #3 on
Fake News Detection
on FNC-1
Common Representation Learning Using Step-based Correlation Multi-Modal CNN
In a broader perspective, the techniques used to investigate common representation learning falls under the categories of canonical correlation-based approaches and autoencoder based approaches.
