8 citations · 10 across the 7 of their papers we have counts for
8 papers
Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers
Fanis Mathioulakis, Gorjan Radevski, Tinne Tuytelaars
We introduce Eff-GRot, an approach for efficient and generalizable rotation estimation from RGB images. Given a query image and a set of reference images with known orientations, o…
On Synthesizing Data for Context Attribution in Question Answering
Gorjan Radevski, Kiril Gashteovski, Shahbaz Syed +11
Question Answering (QA) accounts for a significant portion of LLM usage "in the wild". However, LLMs sometimes produce false or misleading responses, also known as "hallucinations"…
DAVE: Diagnostic benchmark for Audio Visual Evaluation
Gorjan Radevski, Teodora Popordanoska, Matthew B. Blaschko +1
Audio-visual understanding is a rapidly evolving field that seeks to integrate and interpret information from both auditory and visual modalities. Despite recent advances in multi-…
Estimating calibration error under label shift without labels
Teodora Popordanoska, Gorjan Radevski, Tinne Tuytelaars +1
In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems. Calibration error (CE) is an indicator of the alignmen…
Linking Surface Facts to Large-Scale Knowledge Graphs
Gorjan Radevski, Kiril Gashteovski, Chia-Chien Hung +2
Open Information Extraction (OIE) methods extract facts from natural language text in the form of ("subject"; "relation"; "object") triples. These facts are, however, merely surfac…
Multimodal Distillation for Egocentric Action Recognition
Gorjan Radevski, Dusan Grujicic, Marie-Francine Moens +2
The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perfor…
Students taught by multimodal teachers are superior action recognizers
Gorjan Radevski, Dusan Grujicic, Matthew Blaschko +2
The focal point of egocentric video understanding is modelling hand-object interactions. Standard models -- CNNs, Vision Transformers, etc. -- which receive RGB frames as input per…
Revisiting spatio-temporal layouts for compositional action recognition
Gorjan Radevski, Marie-Francine Moens, Tinne Tuytelaars
Recognizing human actions is fundamentally a spatio-temporal reasoning problem, and should be, at least to some extent, invariant to the appearance of the human and the objects inv…