Zobrazeno 1 - 10
of 210
pro vyhledávání: '"Brentari, Diane"'
Autor:
Sandoval-Castaneda, Marcelo, Li, Yanhong, Brentari, Diane, Livescu, Karen, Shakhnarovich, Gregory
This paper presents an in-depth analysis of various self-supervision methods for isolated sign language recognition (ISLR). We consider four recently introduced transformer-based approaches to self-supervised learning from videos, and four pre-traini
Externí odkaz:
http://arxiv.org/abs/2309.02450
Existing work on sign language translation - that is, translation from sign language videos into sentences in a written language - has focused mainly on (1) data collected in a controlled environment or (2) data in a specific domain, which limits the
Externí odkaz:
http://arxiv.org/abs/2205.12870
Natural language processing for sign language video - including tasks like recognition, translation, and search - is crucial for making artificial intelligence technologies accessible to deaf individuals, and is gaining research interest in recent ye
Externí odkaz:
http://arxiv.org/abs/2203.13291
Fingerspelling, in which words are signed letter by letter, is an important component of American Sign Language. Most previous work on automatic fingerspelling recognition has assumed that the boundaries of fingerspelling regions in signing videos ar
Externí odkaz:
http://arxiv.org/abs/2104.01291
Autor:
Shi, Bowen, Del Rio, Aurora Martinez, Keane, Jonathan, Brentari, Diane, Shakhnarovich, Greg, Livescu, Karen
Sign language recognition is a challenging gesture sequence recognition problem, characterized by quick and highly coarticulated motion. In this paper we focus on recognition of fingerspelling sequences in American Sign Language (ASL) videos collecte
Externí odkaz:
http://arxiv.org/abs/1908.10546
Autor:
Shi, Bowen, Del Rio, Aurora Martinez, Keane, Jonathan, Michaux, Jonathan, Brentari, Diane, Shakhnarovich, Greg, Livescu, Karen
We address the problem of American Sign Language fingerspelling recognition in the wild, using videos collected from websites. We introduce the largest data set available so far for the problem of fingerspelling recognition, and the first using natur
Externí odkaz:
http://arxiv.org/abs/1810.11438
Autor:
Kim, Taehwan, Keane, Jonathan, Wang, Weiran, Tang, Hao, Riggle, Jason, Shakhnarovich, Gregory, Brentari, Diane, Livescu, Karen
We study the problem of recognizing video sequences of fingerspelled letters in American Sign Language (ASL). Fingerspelling comprises a significant but relatively understudied part of ASL. Recognizing fingerspelling is challenging for a number of re
Externí odkaz:
http://arxiv.org/abs/1609.07876