5 papers
Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
Luc P. J. Sträter, Hazel Doughty
Parameter-efficient fine-tuning (PEFT) and probing enable adaptation of foundation models using only a small number of trainable parameters, making it attractive for video understa…
Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding
Kaiting Liu, Hazel Doughty
Video recognition models are typically trained on fixed taxonomies which are often too coarse, collapsing distinctions in object, manner or outcome under a single label. As tasks a…
Segmenting Collision Sound Sources in Egocentric Videos
Kranti Kumar Parida, Omar Emara, Hazel Doughty +1
Humans excel at multisensory perception and can often recognise object properties from the sound of their interactions. Inspired by this, we propose the novel task of Collision Sou…
SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning
Fida Mohammad Thoker, Letian Jiang, Chen Zhao +4
Continued advances in self-supervised learning have led to significant progress in video representation learning, offering a scalable alternative to supervised approaches by removi…
HD-EPIC: A Highly-Detailed Egocentric Video Dataset
Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha +16
We present a validation dataset of newly-collected kitchen-based egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe…