O
Oscar Koller
Researcher at Microsoft
Publications - 40
Citations - 3491
Oscar Koller is an academic researcher from Microsoft. The author has contributed to research in topics: Sign language & Gesture recognition. The author has an hindex of 21, co-authored 37 publications receiving 2075 citations. Previous affiliations of Oscar Koller include INESC-ID & University of Surrey.
Papers
More filters
Proceedings ArticleDOI
Neural Sign Language Translation
TL;DR: This work formalizes SLT in the framework of Neural Machine Translation (NMT) for both end-to-end and pretrained settings (using expert knowledge) and allows to jointly learn the spatial representations, the underlying language model, and the mapping between sign and spoken language.
Journal ArticleDOI
Continuous Sign Language Recognition: Towards Large Vocabulary Statistical Recognition Systems Handling Multiple Signers
TL;DR: This work presents a statistical recognition approach performing large vocabulary continuous sign language recognition across different signers, and is the first time system design on a large data set with true focus on real-life applicability is thoroughly presented.
Proceedings ArticleDOI
Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data is Continuous and Weakly Labelled
TL;DR: This work presents a new approach to learning a framebased classifier on weakly labelled sequence data by embedding a CNN within an iterative EM algorithm, which allows the CNN to be trained on a vast number of example images when only loose sequence level information is available for the source videos.
Proceedings ArticleDOI
Sign Language Recognition, Generation, and Translation: An Interdisciplinary Perspective
Danielle Bragg,Oscar Koller,Mary Bellard,Larwan Berke,Patrick Boudreault,Annelies Braffort,Naomi Caselli,Matt Huenerfauth,Hernisa Kacorri,Tessa Verhoef,Christian Vogler,Meredith Ringel Morris +11 more
TL;DR: The results of an interdisciplinary workshop are presented, providing key background that is often overlooked by computer scientists, a review of the state-of-the-art, a set of pressing challenges, and a call to action for the research community.
Proceedings ArticleDOI
SubUNets: End-to-End Hand Shape and Continuous Sign Language Recognition
TL;DR: A novel deep learning approach to solve simultaneous alignment and recognition problems (referred to as “Sequence-to-sequence” learning) is proposed, which decompose the problem into a series of specialised expert systems referred to as SubUNets, and serves to significantly improve the performance of the overarching recognition system.