104 citations · 114 across the 5 of their papers we have counts for
3 papers · 1 filter
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…
Commands 4 Autonomous Vehicles (C4AV) Workshop Summary
Thierry Deruyttere, Simon Vandenhende, Dusan Grujicic +5
The task of visual grounding requires locating the most relevant region or object in an image, given a natural language query. So far, progress on this task was mostly measured on…