@inproceedings{neidle:12011:sign-lang:lrec, author = {Neidle, Carol and Thangali, Ashwin and Sclaroff, Stan}, title = {Challenges in Development of the {American} {Sign} {Language} Lexicon Video Dataset ({ASLLVD}) Corpus}, pages = {143--150}, editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon}, maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {27}, month = may, year = {2012}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12011.html}, abstract = {The American Sign Language Lexicon Video Dataset (ASLLVD) consists of videos of >3,300 ASL signs in citation form, each produced by 1-6 native ASL signers, for a total of almost 9,800 tokens. This dataset, including multiple synchronized videos showing the signing from different angles, will be shared publicly once the linguistic annotations and verifications are complete. Linguistic annotations include gloss labels, sign start and end time codes, start and end handshape labels for both hands, morphological and articulatory classifications of sign type. For compound signs, the dataset includes annotations for each morpheme. To facilitate computer vision-based sign language recognition, the dataset also includes numeric ID labels for sign variants, video sequences in uncompressed-raw format, camera calibration sequences, and software for skin region extraction. We discuss here some of the challenges involved in the linguistic annotations and categorizations. We also report an example computer vision application that leverages the ASLLVD: the formulation employs a HandShapes Bayesian Network (HSBN), which models the transition probabilities between start and end handshapes in monomorphemic lexical signs. Further details and statistics for the ASLLVD dataset, as well as information about annotation conventions, are available from http://www.bu.edu/asllrp/lexicon.} } @inproceedings{athitsos:10022:sign-lang:lrec, author = {Athitsos, Vassilis and Neidle, Carol and Sclaroff, Stan and Nash, Joan and Stefan, Alexandra and Thangali, Ashwin and Wang, Haijing and Yuan, Quan}, title = {Large Lexicon Project: {American} {Sign} {Language} Video Corpus and Sign Language Indexing/Retrieval Algorithms}, pages = {11--14}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10022.html}, abstract = {When we encounter a word that we do not understand in a written language, we can look it up in a dictionary. However, looking up the meaning of an unknown sign in American Sign Language (ASL) is not nearly as straightforward. This paper describes progress in an ongoing project aiming to build a computer vision system that helps users look up the meaning of an unknown ASL sign. When a user encounters an unknown ASL sign, the user submits a video of that sign as a query to the system. The system evaluates the similarity between the query and video examples of all signs in the known lexicon, and presents the most similar signs to the user. The user can then look at the retrieved signs and determine if any of them matches the query sign. \par An important part of the project is building a video database containing examples of a large number of signs. So far we have recorded at least two video examples for almost all of the 3,000 signs contained in the Gallaudet dictionary. Each video sequence is captured simultaneously from four different cameras, providing two frontal views, a side view, and a view zoomed in on the face of the signer. Our entire video dataset is publicly available on the Web. \par Automatic computer vision-based evaluation of similarity between signs is a challenging task. In order to improve accuracy, we manually annotate the hand locations in each frame of each sign in the database. While this is a time-consuming process, this process incurs a one-time preprocessing cost that is invisible to the end-user of the system. At runtime, once the user has submitted the query video, the current version of the system asks the user to specify hand locations in the first frame, and then the system automatically tracks the location of the hands in the rest of the query video. The user can review and correct the hand location results. Every correction that the user makes on a specific frame is used by the system to further improve the hand location estimates in other frames. \par Once hand locations have been estimated for the query video, the system evaluates the similarity between the query video and every sign video in the database. Similarity is measured using the Dynamic Time Warping (DTW) algorithm, a well-known algorithm for comparing time series. The performance of the system has been evaluated in experiments where 933 signs from 921 distinct sign classes are used as the dataset of known signs, and 193 signs are used as a test set. In those experiments, only a single frontal view was used for all test and training examples. For 68{\%} of the test signs, the correct sign is included in the 20 most similar signs retrieved by the system. \par In ongoing work, we are manually annotating hand locations in the remainder of our collected videos, so as to gradually incorporate more signs into our system. We are also investigating better ways for measuring similarity between signs, and for making the system more automatic, reducing or eliminating the need for the user to manually provide information to the system about hand locations.} } @inproceedings{gavrilov-etal-2012-detecting:lrec, author = {Gavrilov, Zoya and Sclaroff, Stan and Neidle, Carol and Dickinson, Sven}, title = {Detecting Reduplication in Videos of {A}merican {S}ign {L}anguage}, pages = {3767--3773}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Istanbul, Turkey}, day = {21--27}, month = may, year = {2012}, isbn = {978-2-9517408-7-7}, language = {english}, url = {https://aclanthology.org/L12-1057}, abstract = {A framework is proposed for the detection of reduplication in digital videos of American Sign Language (ASL). In ASL, reduplication is used for a variety of linguistic purposes, including overt marking of plurality on nouns, aspectual inflection on verbs, and nominalization of verbal forms. Reduplication involves the repetition, often partial, of the articulation of a sign. In this paper, the apriori algorithm for mining frequent patterns in data streams is adapted for finding reduplication in videos of ASL. The proposed algorithm can account for varying weights on items in the apriori algorithm's input sequence. In addition, the apriori algorithm is extended to allow for inexact matching of similar hand motion subsequences and to provide robustness to noise. The formulation is evaluated on 105 lexical signs produced by two native signers. To demonstrate the formulation, overall hand motion direction and magnitude are considered; however, the formulation should be amenable to combining these features with others, such as hand shape, orientation, and place of articulation.} } @inproceedings{dreuw-etal-2008-benchmark:lrec, author = {Dreuw, Philippe and Neidle, Carol and Athitsos, Vassilis and Sclaroff, Stan and Ney, Hermann}, title = {Benchmark Databases for Video-Based Automatic Sign Language Recognition}, pages = {1115--1120}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1469}, abstract = {A new, linguistically annotated, video database for automatic sign language recognition is presented. The new RWTH-BOSTON-400 corpus, which consists of 843 sentences, several speakers and separate subsets for training, development, and testing is described in detail. For evaluation and benchmarking of automatic sign language recognition, large corpora are needed. Recent research has focused mainly on isolated sign language recognition methods using video sequences that have been recorded under lab conditions using special hardware like data gloves. Such databases have often consisted generally of only one speaker and thus have been speaker-dependent, and have had only small vocabularies. A new database access interface, which was designed and created to provide fast access to the database statistics and content, makes it possible to easily browse and retrieve particular subsets of the video database. Preliminary baseline results on the new corpora are presented. In contradistinction to other research in this area, all databases presented in this paper will be publicly available.} }