Fredom: Fairness domain adaptation approach to semantic scene understanding

TD Truong, N Le, B Raj, J Cothren… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Although Domain Adaptation in Semantic Scene Segmentation has shown
impressive improvement in recent years, the fairness concerns in the domain adaptation …

Public health advocacy dataset: A dataset of tobacco usage videos from social media

NVS Chappa, C McCormick, SR Gongora… - arxiv preprint arxiv …, 2024 - arxiv.org
The Public Health Advocacy Dataset (PHAD) is a comprehensive collection of 5,730 videos
related to tobacco products sourced from social media platforms like TikTok and YouTube …

Learning from Oversampling: A Systematic Exploitation of oversampling to address Data Scarcity issues in Deep Learning based Magnetic Resonance Image …

IK Jalata, R Khan, U Nakarmi - IEEE Access, 2024 - ieeexplore.ieee.org
Data acquisitions in Magnetic Resonance Imaging (MRI) are inherently slow due to
sequential acquisition protocol. Image reconstruction from under-sampled data is posed as …

Flaash: Flow-attention adaptive semantic hierarchical fusion for multi-modal tobacco content analysis

NVS Chappa, PD Dobbs, B Raj, K Luu - arxiv preprint arxiv:2410.19896, 2024 - arxiv.org
The proliferation of tobacco-related content on social media platforms poses significant
challenges for public health monitoring and intervention. This paper introduces a novel multi …

Semi-supervised learning for fish species recognition

SY Alaba, C Shah, MM Nabi, JE Ball… - ocean sensing and …, 2023 - spiedigitallibrary.org
Fish species recognition and detection are essential for fishery industries. Accurate and
robust species classification and detection play a vital role in monitoring fish activities and …

Real-world image deblurring via unsupervised domain adaptation

H Liu, B Li, M Lu, Y Wu - International Symposium on Visual Computing, 2023 - Springer
Most deep learning models for image deblurring are trained on pairs of clean images and
their blurry counterparts, where the blurry inputs are artificially generated. However, it is …

VAEWGAN-NCO in image deblurring framework using variational autoencoders and Wasserstein generative adversarial network

A Ranjan, M Ravinder - Signal, Image and Video Processing, 2024 - Springer
This article proposes a novel “Deep Salient Image Deblurring (DSID) Framework” for kernel-
free image deblurring that combines saliency detection and variational autoencoders and …

When System Model Meets Image Prior: An Unsupervised Deep Learning Architecture for Accelerated Magnetic Resonance Imaging

I Jalata, U Nakarmi - International Symposium on Visual Computing, 2023 - Springer
Abstract Magnetic Resonance Imaging (MRI) is typically a slow process because of its
sequential data acquisition. To speed up this process, MR acquisition is often accelerated by …

LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition

NVSR Chappa, K Luu - arxiv preprint arxiv:2410.21108, 2024 - arxiv.org
Group Activity Recognition (GAR) remains challenging in computer vision due to the
complex nature of multi-agent interactions. This paper introduces LiGAR, a LIDAR-Guided …

The Surprising Effectiveness of Deep Orthogonal Procrustes Alignment in Unsupervised Domain Adaptation

K Thopalli, R Anirudh, P Turaga, JJ Thiagarajan - IEEE Access, 2023 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a
labeled source domain to an unlabeled target domain. Traditionally, geometry-based …