SLTAT 2023: 8th Workshop on Sign Language Translation and Avatar Technologies


8:45 Welcome
9:00 On-stage presentation 1 (Eleni Efthimiou, Athena RC Athens GR, session chair)
  • A text-to-SL translation and synthesis system using 3D avatar technology
    - Sylvie Gibet (Universite Bretagne Sud)
  • Improving 3D pose estimation for sign language
    - Maksym Ivashechkin (University of Surrey)
    - Oscar Mendez (University of Surrey)
    - Richard Bowden (University of Surrey)
  • 10:00 Coffee break AM
    10:30 Announcements
    10:40 Elevator Pitches for Poster Session I
    10:50 Poster Session I (John McDonald, DePaul University Chicago USA, session chair)
    • WP-B-1: Do predictability factors towards signing avatars hold across cultures?
      - Abdelhadi Soudi (ENSMR)
      - Manal El hakkaoui (ENMSR)
      - Kristof Van Laerhoven (University of Siegen)
    • WP-B-2: Automatic alignment between sign language videos and motion capture data: a motion energy-based approach
      - Fabrizio Nunnari (DFKI GmbH)
      - Mina Ameli (DFKI GmbH)
      - Shailesh Mishra (DFKI GmbH)
    • WP-B-3: Augmenting glosses with geometrical inflection parameters for the animation of sign language avatars
      - Fabrizio Nunnari (DFKI GmbH)
      - Mishra Shailesh (DFKI GmbH)
      - Patrick Gebhard (DFKI Germany)
    • WP-B-4: Gloss alignment using word embeddings
      - Harry Walsh (University of Surrey)
      - Ozge Mercanoglu Sincan (University of Surrey)
      - Ben Saunders (University of Surrey)
      - Richard Bowden (University of Surrey)
    • WP-B-5: Machine translation to sign language using post-translation replacement without placeholders
      - Taro Miyazaki (NHK Science & Technology Research Laboratories)
      - Naoki Nakatani (NHK Science & Technology Research Laboratories)
      - Tsubasa Uchida (NHK Science & Technology Research Laboratories)
      - Hiroyuki Kaneko (NHK Science & Technology Research Laboratories)
      - Masanori Sano (NHK)
    • WP-B-6: Leveraging large language models with vocabulary sharing for sign language translation
      - Huije Lee (Korea Advanced Institute of Science and Technology)
      - Jung-Ho Kim (KAIST)
      - Eui Jun Hwang (KAIST)
      - Jaewoo Kim (KAIST)
      - Jong C. Park (KAIST)
    • WP-B-7: Isolated Korean sign gloss recognition: The phonological base
      - Hyun Lee Electronics and Telecommunications Research Institute(ETRI)
      - Han-kyu Lee (ETRI)
      - Chung Hyun Ahn (ETRI)
      - Wonjae Lee (ETRI)
    • WP-B-8: SL-REDU GSL: A large Greek sign language recognition corpus
      - Katerina Papadimitriou (University of Thessaly)
      - Galini Sapountzaki (University of Thessaly)
      - Kyriaki Vasilaki (ATHENA RC / Institute for Language and Speech Processing)
      - Eleni Efthimiou (ATHENA RC / Institute for Language and Speech Processing)
      - Stavroula-Evita Fotinea (ATHENA RC / Institute for Language and Speech Processing)
      - Gerasimos Potamianos (ECE, University of Thessaly)
    • WP-B-9: TrueDepth measurements of facial expressions: Sensitivity to the angle between camera and face
      - Lyke D Esselink (University of Amsterdam)
      - Marloes Oomen (University of Amsterdam)
      - Floris Roelofsen (University of Amsterdam)
    • WP-B-10: The sign language interchange format: Harmonising sign language datasets for computational processing
      - Marc Schulder (Universität Hamburg)
      - Sam Bigeard (Universität Hamburg)
      - Thomas Hanke (Universität Hamburg)
      - Maria Kopf (Universität Hamburg)
    12:00 Lunch break
    14:00 Elevator pitches for Poster Session II
    14:10 Poster Session II (Thomas Hanke, University of Hamburg Hamburg DE, session chair)
    • WP-B-1: Towards incorporating 3D space-awareness into an augmented reality sign language interpreter
      - Fabrizio Nunnari (DFKI GmbH)
      - Eleftherios Avramidis (DFKI GmbH)
      - Vemburaj Chockalingam Yadav (DFKI GmbH)
      - Alain Pagani (DFKI)
      - Yasser Hamidullah (DFKI GmbH)
      - Sepideh Mollanorozy (DFKI GmbH)
      - Cristina España_i_Bonet (DFKI GmbH)
      - Emil Woop (DFKI GmbH)
      - Patrick Gebhard (DFKI, Germany)
    • WP-B-2: EASIER notation: A proposal for a gloss-based scripting language for sign language generation based on lexical data
      - Thomas Hanke (Universität Hamburg)
      - Lutz König (Universität Hamburg)
      - Reiner Konrad (Universität Hamburg)
      - Maria Kopf (Universität Hamburg)
      - Marc Schulder (Universität Hamburg)
    • WP-B-3: Sign language avatar animation search: An Ani2Ani search application
      - Mathew J Huerta-Enochian (EQ4ALL)
      - Changyong Ko (EQ4ALL)
    • WP-B-4: Querying a sign language dictionary with videos using dense vector search
      - Mathieu De Coster (Ghent University)
      - Joni Dambre (Ghent University)
    • WP-B-5: When (shared) space and time don't matter: Remote video-mediated (synchronous and asynchronous) communication in Flemish Sign Language
      - Lien Soetemans (KU Leuven )
      - Myriam Vermeerbergen (KU Leuven)
    • WP-B-6: Distractor-based evaluation of sign spotting
      - Natalie Hollain (Radboud University)
      - Martha Larson (Radboud University)
      - Floris Roelofsen (University of Amsterdam)
    • WP-B-7: Asymmetry in transition times in sign languages
      - Nicole Barnekow (DePaul University)
      - Meaghan Lidd (DePaul University)
      - Deannia Lucas (DePaul University)
      - John C McDonald (DePaul University)
    • WP-B-8: Extending morphs in AZee using pose space deformations
      - Paritosh Sharma (CNRS)
      - Michael Filhol (CNRS)
    • WP-B-9: A method for generating a non-manual feature model for sign language processing
      - Robert G Smith (Technological University Dublin)
      - Markus Hofmann (Technological University Dublin)
    • WP-B-10: Motion editing tool for reproducing grammatical elements of Japanese Sign Language avatar animation
      - Tsubasa Uchida (NHK Science & Technology Research Laboratories)
      - Naoki Nakatani (NHK Science & Technology Research Laboratories)
      - Taro Miyazaki (NHK Science & Technology Research Laboratories)
      - Hiroyuki Kaneko (NHK Science & Technology Research Laboratories)
      - Masanori Sano (NHK)
    • WP-B-11: Recognizing highly variable American Sign Language in virtual reality
      - Md Shahinur Alam (Gallaudet University)
      - Myles Bastion (CymaSpace)
      - Melissa Malzkuhn (Gallaudet University)
      - Lorna C Quandt (Gallaudet University)
    15:30 Coffee break PM
    16:00 On-stage presentation II (Kevin Lee, EQ4ALL Seoul KR, session chair)
    • Representation matters: The case for diversifying sign language avatars
      - Maria Kopf (Universität Hamburg)
      - Rehana Omardeen (European Union of the Deaf)
      - Davy Van Landuyt (European Union of the Deaf)
    16:30 Forum: What would make a good avatar challenge?