Our partner University of Surrey participated in the European Conference on Computer Vision (ECCV 2022), held in Tel Aviv, Israel, and online from 23 to 27 October 2022.
There were two half-day workshops on sign language at the ECCV2022 in Tel Aviv. EASIER was represented at both of them (signlanguageworkshop.github.io).
2022 Open Challenges in Continuous Sign Language Recognition Workshop at ECCV
In the morning was the ChaLearn workshop. Richard Bowden, from University of Surrey, was one of the invited speakers where he spoke about his work into sign language recognition and production and discussed the EASIER project. Other speakers were Annelies Braffort (LIMSI), Lale Akarun (Bogazici University) and Andrew Zisserman (Oxford University).
Ryan Wong, from University of Surrey and funded by EASIER, was the winner of Track 1 “MSSL – Multiple Shot Supervised Learning” competition at the 2022 Sign Spotting Challenge. MSSL is a classical machine learning Track where signs to be spotted are the same in training, validation and test sets. The three sets will contain samples of signs cropped from the continuous stream of Spanish sign language, meaning that all of them have co-articulation influence. The training set contains the begin-end timestamps (in milisecs) annotated by a deaf person and a SL-interpreter with a homogeneous criterion of multiple instances for each of the query signs. Participants will need to spot those signs in a set of validation videos with captured annotations. The annotations will be released when delivering the set of test videos. The annotations of the test set will be released after the challenge has finished. The signers in the test set can be the same or different to the training and validation set. Signers are men, women, right and left-handed.
SLRTP 2022: Sign Language Recognition, Translation and Production Workshop
In the afternoon the Surrey team co-organised a second workshop (SLRTP 2022) on sign language with DCAL and Oxford University. This workshop had 4 keynote speakers: Sarah Ebling (University of Zurich), Mark Wheatley (EUD), Melissa Malzkuhn (Gallaudet University) and Adam Munder (Omnibridge/Intel).
Both Sarah Eblign and Mark Wheatley talked about their involvement in the EASIER project.
