6 papers
Multi-channel Transformers for Multi-articulatory Sign Language Translation
Necati Cihan Camgoz, Oscar Koller, Simon Hadfield +1
Sign languages use multiple asynchronous information channels (articulators), not just the hands but also the face and body, which computational approaches often ignore. In this pa…
Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation
Necati Cihan Camgoz, Oscar Koller, Simon Hadfield +1
Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performa…
DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning
Jaime Spencer, Richard Bowden, Simon Hadfield
In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack…
Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance
Jaime Spencer, Richard Bowden, Simon Hadfield
"Like night and day" is a commonly used expression to imply that two things are completely different. Unfortunately, this tends to be the case for current visual feature representa…
Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
Jaime Spencer, Richard Bowden, Simon Hadfield
How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question.…
Localisation via Deep Imagination: learn the features not the map
Jaime Spencer, Oscar Mendez, Richard Bowden +1
How many times does a human have to drive through the same area to become familiar with it? To begin with, we might first build a mental model of our surroundings. Upon revisiting…