Search Results - "Sadovnik, Amir"

MSDU-Net: A Multi-Scale Dilated U-Net for Blur Detection by Xiao, Xiao, Yang, Fan, Sadovnik, Amir

“…A blur detection problem which aims to separate the blurred and clear regions of an image is widely used in many important computer vision tasks such object…”
Get full text

Where do emotions come from? Predicting the Emotion Stimuli Map by Kuan-Chuan Peng, Sadovnik, Amir, Gallagher, Andrew, Tsuhan Chen

“…Which parts of an image evoke emotions in an observer? To answer this question, we introduce a novel problem in computer vision - predicting an Emotion Stimuli…”
Get full text

A simulated experiment to explore robotic dialogue strategies for people with dementia by Yuan, Fengpei, Sadovnik, Amir, Zhang, Ran, Casenhiser, Devin, Paek, Eun Jin, Zhao, Xiaopeng

“…Introduction Persons with dementia (PwDs) often show symptoms of repetitive questioning, which brings great burdens on caregivers. Conversational robots hold…”
Get full text

Fast, low-memory detection and localization of large, polymorphic inversions from SNPs by Nowling, Ronald J, Fallas-Moya, Fabian, Sadovnik, Amir, Emrich, Scott, Aleck, Matthew, Leskiewicz, Daniel, Peters, John G

“…Large (>1 Mb), polymorphic inversions have substantial impacts on population structure and maintenance of genotypes. These large inversions can be detected…”
Get full text

Data-driven inference of low-order isostable-coordinate-based dynamical models using neural networks by Ahmed, Talha, Sadovnik, Amir, Wilson, Dan

“…The isostable coordinate system, which encodes for level sets of the slowest decaying eigenmodes of the Koopman operator, provides an effective framework with…”
Get full text

Heterogeneous Attention Nested U-Shaped Network for Blur Detection by Guo, Wenliang, Xiao, Xiao, Hui, Yilong, Yang, Wenming, Sadovnik, Amir

“…With the popularity of image sensors in various mobile devices, image blurring caused by hand shaking or out of focus becomes ubiquitous, which deteriorates…”
Get full text

A mixed bag of emotions: Model, predict, and transfer emotion distributions by Kuan-Chuan Peng, Tsuhan Chen, Sadovnik, Amir, Gallagher, Andrew

“…This paper explores two new aspects of photos and human emotions. First, we show through psychovisual studies that different people have different emotional…”
Get full text

Object Detection in Pineapple Fields Drone Imagery Using Few Shot Learning and the Segment Anything Model by Fallas-Moya, Fabian, Calderon-Ramirez, Saul, Sadovnik, Amir, Qi, Hairong

“…Deep Learning Object Detection relies on extensive, manual annotation of datasets, a time-consuming and costly process prone to human inconsistencies…”
Get full text

Monocular Depth Estimation with Adaptive Geometric Attention by Naderi, Taher, Sadovnik, Amir, Hayward, Jason, Qi, Hairong

“…ingle image depth estimation is an ill-posed problem. That is, it is not mathematically possible to uniquely estimate the 3rd dimension (or depth) from a…”
Get full text

Image level color classification for colorblind assistance by Fuller, Thomas L., Sadovnik, Amir

“…The advancement and proliferation of augmented reality lends itself to the development of novel techniques for assistive technologies, especially in the realm…”
Get full text

Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing by Sadovnik, Amir, Gallagher, Andrew, Parikh, Devi, Tsuhan Chen

“…In recent years, there has been a great deal of progress in describing objects with attributes. Attributes have proven useful for object recognition, image…”
Get full text

A visual dictionary attack on Picture Passwords by Sadovnik, Amir, Chen, Tsuhan

“…Microsoft's Picture Password provides a method to authenticate a user without the need of typing a character based password. The password consists of a set of…”
Get full text

Does it matter if empathic AI has no empathy? by Shteynberg, Garriy, Halpern, Jodi, Sadovnik, Amir, Garthoff, Jon, Perry, Anat, Hay, Jessica, Montemayor, Carlos, Olson, Michael A., Hulsey, Tim L., Fairweather, Abrol

Get full text

TopKConv: Increased Adversarial Robustness Through Deeper Interpretability by Eigen, Henry, Sadovnik, Amir

“…Vulnerability to adversarial inputs remains an issue for deep neural networks. Attackers can slightly modify inputs in order to cause adverse behavior in…”
Get full text

Advancing NLP Security by Leveraging LLMs as Adversarial Engines by Srinivasan, Sudarshan, Mahbub, Maria, Sadovnik, Amir

“…This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse…”
Get full text

Redefining "Hallucination" in LLMs: Towards a psychology-informed framework for mitigating misinformation by Berberette, Elijah, Hutchins, Jack, Sadovnik, Amir

“…In recent years, large language models (LLMs) have become incredibly popular, with ChatGPT for example being used by over a billion users. While these models…”
Get full text

Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images by Daw, Arka, Chung, Megan Hong-Thanh, Mahbub, Maria, Sadovnik, Amir

“…Machine learning models are known to be vulnerable to adversarial attacks, but traditional attacks have mostly focused on single-modalities. With the rise of…”
Get full text

It's Not Polite to Point: Describing People with Uncertain Attributes by Sadovnik, Amir, Gallagher, Andrew, Tsuhan Chen

“…Visual attributes are powerful features for many different applications in computer vision such as object detection and scene recognition. Visual attributes…”
Get full text

Hierarchical object groups for scene classification by Sadovnik, A., Tsuhan Chen

“…The hierarchical structures that exist in natural scenes have been utilized for many tasks in computer vision. The basic idea is that instead of using strictly…”
Get full text

ConFUSE: Confusion-based Federated Unlearning with Salience Exploration by Meerza, Syed Irfan Ali, Sadovnik, Amir, Liu, Jian

“…The increasing scale and complexity of deep neural networks, coupled with heightened privacy concerns, has under-scored the importance of developing techniques…”
Get full text