We present a new approach for isolated sign recognition, which combines a spatial-temporal Graph Convolution Network (GCN) architecture for modeling human skeleton keypoints with late fusion of both the forward and backward video streams, and we explore the use of curriculum learning. We employ a type of curriculum learning that dynamically estimates, during training, the order of difficulty of each input video for sign recognition; this involves learning a new family of data parameters that are dynamically updated during training. The research makes use of a large combined video dataset for American Sign Language (ASL), including data from both the American Sign Language Lexicon Video Dataset (ASLLVD) and the Word-Level American Sign Language (WLASL) dataset, with modified gloss labeling of the latter—to ensure 1-1 correspondence between gloss labels and distinct sign productions, as well as consistency in gloss labeling across the two datasets. This is the first time that these two datasets have been used in combination for isolated sign recognition research. We also compare the sign recognition performance on several different subsets of the combined dataset, varying in, e.g., the minimum number of samples per sign (and therefore also in the total number of sign classes and video examples).

The WLASL purports to be “the largest video dataset for Word-Level American Sign Language (ASL) recognition.” It brings together various publicly shared video collections that could be quite valuable for sign recognition research, and it has been used extensively for such research. However, a critical problem with the accompanying annotations has heretofore not been recognized by the authors, nor by those who have exploited these data: There is no 1-1 correspondence between sign productions and gloss labels. Here we describe a large (and recently expanded and enhanced), linguistically annotated, downloadable, video corpus of citation-form ASL signs shared by the American Sign Language Linguistic Research Project (ASLLRP)—with 23,452 sign tokens and an online Sign Bank—in which such correspondences are enforced. We furthermore provide annotations for 19,672 of the WLASL video examples consistent with ASLLRP glossing conventions. For those wishing to use WLASL videos, this provides a set of annotations that makes it possible: (1) to use those data reliably for computational research; and/or (2) to combine the WLASL and ASLLRP datasets, creating a combined resource that is larger and richer than either of those datasets individually, with consistent gloss labeling for all signs. We also offer a summary of our own sign recognition research to date that exploits these data resources.

Deaf signers who wish to communicate in their native language frequently share videos on the Web. However, videos cannot preserve privacy—as is often desirable for discussion of sensitive topics—since both hands and face convey critical linguistic information and therefore cannot be obscured without degrading communication. Deaf signers have expressed interest in video anonymization that would preserve linguistic content. However, attempts to develop such technology have thus far shown limited success. We are developing a new method for such anonymization, with input from ASL signers. We modify a motion-based image animation model to generate high-resolution videos with the signer identity changed, but with the preservation of linguistically significant motions and facial expressions. An asymmetric encoder-decoder structured image generator is used to generate the high-resolution target frame from the low-resolution source frame based on the optical flow and confidence map. We explicitly guide the model to attain a clear generation of hands and faces by using bounding boxes to improve the loss computation. FID and KID scores are used for the evaluation of the realism of the generated frames. This technology shows great potential for practical applications to benefit deaf signers.

To improve computer-based recognition from video of isolated signs from American Sign Language (ASL), we propose a new skeleton-based method that involves explicit detection of the start and end frames of signs, trained on the ASLLVD dataset; it uses linguistically relevant parameters based on the skeleton input. Our method employs a bidirectional learning approach within a Graph Convolutional Network (GCN) framework. We apply this method to the WLASL dataset, but with corrections to the gloss labeling to ensure consistency in the labels assigned to different signs; it is important to have a 1-1 correspondence between signs and text-based gloss labels. We achieve a success rate of 77.43% for top-1 and 94.54% for top-5 using this modified WLASL dataset. Our method, which does not require multi-modal data input, outperforms other state-of-the-art approaches on the same modified WLASL dataset, demonstrating the importance of both attention to the start and end frames of signs and the use of bidirectional data streams in the GCNs for isolated sign recognition.

In American Sign Language (ASL) as well as other signed languages, different classes of signs (e.g., lexical signs, fingerspelled signs, and classifier constructions) have different internal structural properties. Continuous sign recognition accuracy can be improved through use of distinct recognition strategies, as well as different training datasets, for each class of signs. For these strategies to be applied, continuous signing video needs to be segmented into parts corresponding to particular classes of signs. In this paper we present a multiple instance learning-based segmentation system that accurately labels 91.27% of the video frames of 500 continuous utterances (including 7 different subjects) from the publicly accessible NCSLGR corpus (Neidle and Vogler, 2012). The system uses novel feature descriptors derived from both motion and shape statistics of the regions of high local motion. The system does not require a hand tracker.

Current approaches to sign recognition by computer generally have at least some of the following limitations: they rely on laboratory conditions for sign production, are limited to a small vocabulary, rely on 2D modeling (and therefore cannot deal with occlusions and off-plane rotations), and/or achieve limited success. Here we propose a new framework that (1) provides a new tracking method less dependent than others on laboratory conditions and able to deal with variations in background and skin regions (such as the face, forearms, or other hands); (2) allows for identification of 3D hand configurations that are linguistically important in American Sign Language (ASL); and (3) incorporates statistical information reflecting linguistic constraints in sign production. For purposes of large-scale computer-based sign language recognition from video, the ability to distinguish hand configurations accurately is critical. Our current method estimates the 3D hand configuration to distinguish among 77 hand configurations linguistically relevant for ASL. Constraining the problem in this way makes recognition of 3D hand configuration more tractable and provides the information specifically needed for sign recognition. Further improvements are obtained by incorporation of statistical information about linguistic dependencies among handshapes within a sign derived from an annotated corpus of almost 10,000 sign tokens.

Essential grammatical information is conveyed in signed languages by clusters of events involving facial expressions and movements of the head and upper body. This poses a significant challenge for computer-based sign language recognition. Here, we present new methods for the recognition of nonmanual grammatical markers in American Sign Language (ASL) based on: (1) new 3D tracking methods for the estimation of 3D head pose and facial expressions to determine the relevant low-level features; (2) methods for higher-level analysis of component events (raised/lowered eyebrows, periodic head nods and head shakes) used in grammatical markings―with differentiation of temporal phases (onset, core, offset, where appropriate), analysis of their characteristic properties, and extraction of corresponding features; (3) a 2-level learning framework to combine low- and high-level features of differing spatio-temporal scales. This new approach achieves significantly better tracking and recognition results than our previous methods.

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.

This paper addresses the problem of automatically recognizing linguistically significant nonmanual expressions in American Sign Language from video. We develop a fully automatic system that is able to track facial expressions and head movements, and detect and recognize facial events continuously from video. The main contributions of the proposed framework are the following: (1) We have built a stochastic and adaptive ensemble of face trackers to address factors resulting in lost face track; (2) We combine 2D and 3D deformable face models to warp input frames, thus correcting for any variation in facial appearance resulting from changes in 3D head pose; (3) We use a combination of geometric features and texture features extracted from a canonical frontal representation. The proposed new framework makes it possible to detect grammatically significant nonmanual expressions from continuous signing and to differentiate successfully among linguistically significant expressions that involve subtle differences in appearance. We present results that are based on the use of a dataset containing 330 sentences from videos that were collected and linguistically annotated at Boston University.

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.