Audio Descriptions (AD) are essential for making visual content accessible to individuals with visual impairments. Recent works have shown a promising step towards automating AD, but they have been limited to describing high-quality movie content using human-annotated ground truth AD in the process. In this work, we present an end-to-end pipeline, MCAD, that extends AD generation beyond movies to the domain of sports, with a focus on soccer games, without relying on ground truth AD. To address the absence of domain-specific AD datasets, we fine-tune a Video Large Language Model on publicly available movie AD datasets so that it learns the narrative structure and conventions of AD. During inference, MCAD incorporates multimodal contextual cues such as player identities, soccer events/actions, and commentary from the game. These cues, combined with input prompts to the fine-tuned VideoLLM, allow the system to produce complete AD text for each video segment. We further introduce a new evaluation metric,$A R G E-A D$, designed to accurately assess the quality of generated AD. ARGE-AD evaluates the generated AD for the presence of five characteristics: (i) usage of people's names, (ii) mention of actions/events, (iii) appropriate length of AD, (iv) absence of pronouns, and ($v$) overlap from commentary/subtitles. We present an in-depth analysis of our approach on both movie and soccer datasets. We also validate the use of this metric to quantitatively comment on the quality of generated AD using our metric across domains. Additionally, we contribute audio descriptions for 100 soccer game clips annotated by two AD experts.

Achieving expressive 3D motion reconstruction and automatic generation for isolated sign words can be challenging, due to the lack of real-world 3D sign-word data, the complex nuances of signing motions, and the cross-modal understanding of sign language semantics. To address these challenges, we introduce SignAvatar, a framework capable of both word-level sign language reconstruction and generation. SignAvatar employs a transformer-based conditional variational autoencoder architecture, effectively establishing relationships across different semantic modalities. Additionally, this approach incorporates a curriculum learning strategy to enhance the model's robustness and generalization, resulting in more realistic motions. Furthermore, we contribute the ASL3DWord dataset, composed of 3D joint rotation data for the body, hands, and face, for unique sign words. We demonstrate the effectiveness of SignAvatar through extensive experiments, showcasing its superior reconstruction and automatic generation capabilities. The code and dataset are available on the project page1.

Sign language is a complex visual language, and automatic interpretations of sign language can facilitate communication involving deaf individuals. As one of the essential components of sign language, fingerspelling connects the natural spoken languages to the sign language and expands the scale of sign language vocabulary. In practice, it is challenging to analyze fingerspelling alphabets due to their signing speed and small motion range. The usage of synthetic data has the potential of further improving fingerspelling alphabets analysis at scale. In this paper, we evaluate how different video-based human representations perform in a framework for Alphabet Generation for American Sign Language (ASL). We tested three mainstream video-based human representations: two-stream inflated 3D ConvNet, 3D landmarks of body joints, and rotation matrices of body joints. We also evaluated the effect of different skeleton graphs and selected body joints. The generation process of ASL fingerspelling used a transformer-based Conditional Variational Autoencoder. To train the model, we collected ASL alphabet signing videos from 17 signers with dynamic alphabet signing. The generated alphabets were evaluated using automatic metrics of quality such as FID, and we also considered supervised metrics by recognizing the generated entries using Spatio-Temporal Graph Convolutional Networks. Our experiments show that using the rotation matrices of the upper body joints and the signing hand give the best results for the generation of ASL alphabet signing. Going forward, our goal is to produce articulated fingerspelling words by combining individual alphabets learned in this work.

A true interpreting agent not only understands sign language and translates to text, but also understands text and translates to signs. Much of the AI work in sign language translation to date has focused mainly on translating from signs to text. Towards the latter goal, we propose a text-to-sign translation model, SignNet, which exploits the notion of similarity (and dissimilarity) of visual signs in translating. This module presented is only one part of a dual-learning two task process involving text-to-sign (T2S) as well as sign-to-text (S2T). We currently implement SignNet as a single channel architecture so that the output of the T2S task can be fed into S2T in a continuous dual learning framework. By single channel, we refer to a single modality, the body pose joints. In this work, we present SignNet, a T2S task using a novel metric embedding learning process, to preserve the distances between sign embeddings relative to their dissimilarity. We also describe how to choose positive and negative examples of signs for similarity testing. From our analysis, we observe that metric embedding learning-based model perform significantly better than the other models with traditional losses, when evaluated using BLEU scores. In the task of gloss to pose, SignNet performed as well as its state-of-the-art (SoTA) counterparts and outperformed them in the task of text to pose, by showing noteworthy enhancements in BLEU 1 - BLEU 4 scores (BLEU 1: 31 → 39; ≈26% improvement and BLEU 4: 10.43 →11.84; ≈14% improvement) when tested on the popular RWTH PHOENIX-Weather-2014T benchmark dataset

The role of a sign interpreting agent is to bridge the communication gap between the hearing-only and Deaf or Hard of Hearing communities by translating both from sign language to text and from text to sign language. Until now, much of the AI work in automated sign language processing has focused primarily on sign language to text translation, which puts the advantage mainly on the side of hearing individuals. In this article, we describe advances in sign language processing based on transformer networks. Specifically, we introduce SignNet II, a sign language processing architecture, a promising step towards facilitating two-way sign language communication. It is comprised of sign-to-text and text-to-sign networks jointly trained using a dual learning mechanism. Furthermore, by exploiting the notion of sign similarity, a metric embedding learning process is introduced to enhance the text-to-sign translation performance. Using a bank of multi-feature transformers, we analyzed several input feature representations and discovered that keypoint-based pose features consistently performed well, irrespective of the quality of the input videos. We demonstrated that the two jointly trained networks outperformed their singly-trained counterparts, showing noteworthy enhancements in BLEU-1 - BLEU-4 scores when tested on the largest available German Sign Language (GSL) benchmark dataset.

While a significant amount of work has been done on the commonly used, tightly -constrained weather-based, German sign language (GSL) dataset, little has been done for continuous sign language translation (SLT) in more realistic settings, including American sign language (ASL) translation. Also, while CNN - based features have been consistently shown to work well on the GSL dataset, it is not clear whether such features will work as well in more realistic settings when there are more heterogeneous signers in non-uniform backgrounds. To this end, in this work, we introduce a new, realistic phrase-level ASL dataset (ASLing), and explore the role of different types of visual features (CNN embeddings, human body keypoints, and optical flow vectors) in translating it to spoken American English. We propose a novel Transformer-based, visual feature learning method for ASL translation. We demonstrate the explainability efficacy of our proposed learning methods by visualizing activation weights under various input conditions and discover that the body keypoints are consistently the most reliable set of input features. Using our model, we successfully transfer-learn from the larger GSL dataset to ASLing, resulting in significant BLEU score improvements. In summary, this work goes a long way in bringing together the AI resources required for automated ASL translation in unconstrained environments.