collaborators

6 papers

cs.CV2026

GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation

Shyma Alhuwaider, Yasmeen Alsaedy, Merey Ramazanova +2

Test-time adaptation (TTA) enables a pre-trained model to adapt online to an unlabeled test stream under distribution shift. While most TTA research focuses on the adaptation objec…

cs.CV2026

Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation

Abdelrahman Eldesokey, Merey Ramazanova, Ahmad Sait +4

Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically a…

cs.CV2026

Pixels or Positions? Benchmarking Modalities in Group Activity Recognition

Drishya Karki, Merey Ramazanova, Anthony Cioppa +2

Group Activity Recognition (GAR) is well studied on the video modality for surveillance and indoor team sports (e.g., volleyball, basketball). Yet, other modalities such as agent p…

cs.CV2025

ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking

Shyma Alhuwaider, Motasem Alfarra, Juan C. Perez +2

We introduce a novel tracklet-based dataset for benchmarking test-time adaptation (TTA) methods. The aim of this dataset is to mimic the intricate challenges encountered in real-wo…

cs.CV2025

Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos

Merey Ramazanova, Alejandro Pardo, Bernard Ghanem +1

Understanding videos that contain multiple modalities is crucial, especially in egocentric videos, where combining various sensory inputs significantly improves tasks like action r…

cs.CV2025

OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection

Shuming Liu, Chen Zhao, Fatimah Zohra +10

Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field…