activity
20232026
collaborators

6 papers

cs.LG2026

MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization

Yavuz Yarici, Ghassan AlRegib

Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal dom…

cs.CV2025

Subject Invariant Contrastive Learning for Human Activity Recognition

Yavuz Yarici, Kiran Kokilepersaud, Mohit Prabhushankar +1

The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learn…

cs.CV2025

Hierarchical and Multimodal Data for Daily Activity Understanding

Ghazal Kaviani, Yavuz Yarici, Seulgi Kim +4

Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in…

cs.LG2024

CRACKS: Crowdsourcing Resources for Analysis and Categorization of Key Subsurface faults

Mohit Prabhushankar, Kiran Kokilepersaud, Jorge Quesada +6

Crowdsourcing annotations has created a paradigm shift in the availability of labeled data for machine learning. Availability of large datasets has accelerated progress in common k…

cs.CV2024

Explaining Representation Learning with Perceptual Components

Yavuz Yarici, Kiran Kokilepersaud, Mohit Prabhushankar +1

Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods inef…

cs.CV2024

Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss

Kiran Kokilepersaud, Yavuz Yarici, Mohit Prabhushankar +1

In this work, we propose a novel supervised contrastive loss that enables the integration of taxonomic hierarchy information during the representation learning process. A supervise…