Andy Cǎtrunǎ
YOU?
Author Swipe
View article: MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts
MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts Open
Gait encodes rich biometric and behavioural information, yet leveraging the manner of walking to infer psychological traits remains a challenging and underexplored problem. We introduce a hierarchical Multi-Stage Mixture of Movement Expert…
View article: Database-Agnostic Gait Enrollment using SetTransformers
Database-Agnostic Gait Enrollment using SetTransformers Open
Gait recognition has emerged as a powerful tool for unobtrusive and long-range identity analysis, with growing relevance in surveillance and monitoring applications. Although recent advances in deep learning and large-scale datasets have e…
View article: Aligning Actions and Walking to LLM-Generated Textual Descriptions
Aligning Actions and Walking to LLM-Generated Textual Descriptions Open
Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including data augmentation and synthetic data generation. This work explores the use of LLMs to generate rich textual descriptions for motion seque…
View article: Gait Recognition from Highly Compressed Videos
Gait Recognition from Highly Compressed Videos Open
Surveillance footage represents a valuable resource and opportunities for conducting gait analysis. However, the typical low quality and high noise levels in such footage can severely impact the accuracy of pose estimation algorithms, whic…
View article: The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models
The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models Open
Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the prevailing assumption that vision-based gait recognition, i…
View article: CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild
CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild Open
Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality. Estimating the direction of looking in unconstrained envir…
View article: A Pilot Usability Assessment of a Novel AI Platform for Car Price Estimates
A Pilot Usability Assessment of a Novel AI Platform for Car Price Estimates Open
The Usable Artificial Intelligence (UAI) paradigm holds the promise of bridging the gap between Human-Computer Interaction (HCI) and Artificial Intelligence (AI) developments.This study contributes to the matter by assessing the usability …
View article: Car Full View Dataset: Fine-Grained Predictions of Car Orientation from Images
Car Full View Dataset: Fine-Grained Predictions of Car Orientation from Images Open
The orientation of objects plays an important role in accurate predictions for the tasks of classification, detection, and trajectory estimation. This is especially important in the automotive domain, where estimating an accurate car orien…
View article: GaitPT: Skeletons Are All You Need For Gait Recognition
GaitPT: Skeletons Are All You Need For Gait Recognition Open
The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking patterns have been regarded as a unique fingerprinting meth…
View article: Car Price Quotes Driven by Data-Comprehensive Predictions Grounded in Deep Learning Techniques
Car Price Quotes Driven by Data-Comprehensive Predictions Grounded in Deep Learning Techniques Open
The used car market has a high global economic importance, with more than 35 million cars sold yearly. Accurately predicting prices is a crucial task for both buyers and sellers to facilitate informed decisions in terms of opportunities or…
View article: Car Price Quotes Driven by Data - Comprehensive Predictions Grounded in Deep Learning Techniques
Car Price Quotes Driven by Data - Comprehensive Predictions Grounded in Deep Learning Techniques Open
The used car market has a high global economic importance, with more than 35 million cars sold yearly. Accurately predicting prices is a crucial task for both buyers and sellers to facilitate informed decisions in terms of opportunities or…
View article: Exploring Self-Supervised Vision Transformers for Gait Recognition in the Wild
Exploring Self-Supervised Vision Transformers for Gait Recognition in the Wild Open
The manner of walking (gait) is a powerful biometric that is used as a unique fingerprinting method, allowing unobtrusive behavioral analytics to be performed at a distance without subject cooperation. As opposed to more traditional biomet…
View article: From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patterns
From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patterns Open
Obtaining demographics information from video is valuable for a range of real-world applications. While approaches that leverage facial features for gender inference are very successful in restrained environments, they do not work in most …