Fingerspelling, the manual representation of alphabetic characters, is a core element of sign languages. Learners report that reading back fingerspelling is among the most challenging aspects of learning sign languages, primarily due to limited practice opportunities. This paper presents AuslanSpell, a novel technology designed to enhance proficiency in Australian Sign Language (Auslan) fingerspelling. AuslanSpell allows learners to input any English word and produces 3D animated models that articulate the corresponding Auslan signs, featuring smooth hand transitions. In tests with 33 novice signers, after brief interaction with AuslanSpell, participants performed above chance on beginner multiple-choice tasks, correctly identified first and last letters more often than middle letters in free-text tasks, and reported high satisfaction – especially with features such as adjustable signing speeds and rotatable views. The results confirm AuslanSpell’s potential in enhancing the comprehension and engagement of fingerspelling learners. AuslanSpell will be available through Auslan Signbank and Apple App Store, across iOS, iPadOS, macOS, and the web.

The trend in sign language generation is centered around data-driven generative methods that require vast amounts of precise 2D and 3D human pose data to achieve an acceptable generation quality. However, currently, most sign language datasets are video-based and limited to automatically reconstructed 2D human poses (i.e., keypoints) and lack accurate 3D information. Furthermore, existing state-of-the-art for automatic 3D human pose estimation from sign language videos is prone to self-occlusion, noise, and motion blur effects, resulting in poor reconstruction quality. In response to this, we introduce DexAvatar, a novel framework to reconstruct bio-mechanically accurate fine-grained hand articulations and body movements from in-the-wild monocular sign language videos, guided by learned 3D hand and body priors. DexAvatar achieves strong performance in the SGNify motion capture dataset, the only benchmark available for this task, reaching an improvement of 35.11% in the estimation of body and hand poses compared to the state-of-the-art. The official website of this work is: https://github.com/kaustesseract/DexAvatar.

3D printed models (3DPMs) are increasingly used to support the education of students who are blind or have low vision (BLV). As 3DPMs are more widely-adopted, educators are using more complex multi-part models. However, with this increased complexity comes additional challenges for their use, such as supporting audio labels of multiple parts as well as guiding the assembly and disassembly of the model. This work explores the co-design and evaluation of a system that supports the use of multi-part 3DPMs by BLV students. Working with BLV adults and children, as well as educators, an iPad application was developed to support interaction with an insect model, including speech interaction and support for assembly. Evaluation showed that the system was strongly enjoyed by students and educators were enthusiastic as they believed it would increase classroom engagement and inclusion, and its support for voice annotation could be used for assessment.

High Dynamic Range (HDR) content (i.e., images and videos) has a broad range of applications. However, capturing HDR content from real-world scenes is expensive and time-consuming. Therefore, the challenging task of reconstructing visually accurate HDR images from their Low Dynamic Range (LDR) counterparts is gaining attention in the vision research community. A major challenge is the lack of datasets, which capture diverse scene conditions (e.g., lighting, weather, locations) and various image features (e.g., color, contrast, saturation). To address this gap, we introduce GTA-HDR, a large-scale synthetic dataset of photo-realistic HDR images sampled from the GTA-V video game. We perform thorough evaluation of the proposed dataset, which enables significant qualitative and quantitative improvements of the state-of-the-art HDR image reconstruction methods. Furthermore, we demonstrate the effectiveness of the proposed dataset and its impact on additional computer vision tasks including 3D human pose estimation, human body part segmentation, and holistic scene segmentation. The dataset, data collection pipeline, and evaluation code are available at: https://github.com/HrishavBakulBarua/GTA-HDR.

We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with major challenges in video prediction. These include learning spatiotemporal information, handling high dimensional data, combating blurry prediction, and implicit modeling of physical characteristics. Extensive experimental results on four challenging tasks, namely KTH Human Action, TrafficBJ, Human3.6 M, and Kitti, demonstrate that our model compares favorably against state-of-the-art video prediction techniques both in quantitative and qualitative evaluations despite a much smaller model size. Finally, we boost S-HR-VQVAE by proposing a novel training method to jointly estimate the HR-VQVAE and AST-PM parameters.

High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offers various data-driven methods for HDR image reconstruction from Low Dynamic Range (LDR) counterparts. A common limitation of these approaches is missing details in regions of the reconstructed HDR images, which are overor under-exposed in the input LDR images. To this end, we propose a simple and effective method, HistoHDR-Net, to recover the fine details (e.g., color, contrast, saturation, and brightness) of HDR images via a fusion-based approach utilizing histogram-equalized LDR images along with self-attention guidance. Our experiments demonstrate the efficacy of the proposed approach over the state-of-art methods.

Adults with autism spectrum disorder (ASD) face difficulties in communicating with neurotypical people in their daily lives and workplaces. In addition, research on modeling communication in neurodiverse groups is scarce. To recognize communication difficulties caused by neurodiversity, we first, collected a multimodal corpus for decision-making discussions in neurodiverse groups that included a person with ASD and two neurotypical participants. For corpus analysis, we investigated eye-gaze and facial expression exchanges between individuals with ASD and neurotypical participants during both listening and speaking. The findings were extended to automatically estimate the engagement of ASD individuals. To capture the effect of contingent behaviors between ASD individuals and neurotypical participants, we developed a transformer-based model that considers the participation role by changing the direction of cross-person attention depending on whether the ASD individual is listening or speaking. The proposed approach yields comparable results to the state-of-the-art for engagement estimation in neurotypical group conversations while accounting for the dynamic nature of behavior influence in face-to-face interactions. The code associated with this study is available at https://github.com/IUI-Lab/switch-attention.

The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality deepfake images and videos, only a few works address the problem of the localization of small segments of audio-visual manipulations embedded in real videos. In this research, we emulate the process of such content generation and propose the AV-Deepfake1M dataset. The dataset contains content-driven (i) video manipulations, (ii) audio manipulations, and (iii) audio-visual manipulations for more than 2K subjects resulting in a total of more than 1M videos. The paper provides a thorough description of the proposed data generation pipeline accompanied by a rigorous analysis of the quality of the generated data. The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets. The proposed dataset will play a vital role in building the next-generation deepfake localization methods. The dataset and associated code are available at https://github.com/ControlNet/AV-Deepfake1M.

The detection and localization of deepfake content, particularly when small fake segments are seamlessly mixed with real videos, remains a significant challenge in the field of digital media security. Based on the recently released AV-Deepfake1M dataset, which contains more than 1 million manipulated videos across more than 2,000 subjects, we introduce the 1M-Deepfakes Detection Challenge. This challenge is designed to engage the research community in developing advanced methods for detecting and localizing deepfake manipulations within the large-scale high-realistic audio-visual dataset. The participants can access the AV-Deepfake1M dataset and are required to submit their inference results for evaluation across the metrics for detection or localization tasks. The methodologies developed through the challenge will contribute to the development of next-generation deepfake detection and localization systems. Evaluation scripts, baseline models, and accompanying code will be available on https://github.com/ControlNet/AV-Deepfake1M.

This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS). Our proposed framework, named MARLIN, is a facial video masked autoencoder, that learns highly robust and generic facial embeddings from abundantly available non-annotated web crawled facial videos. As a challenging auxiliary task, MARLIN reconstructs the spatio-temporal details of the face from the densely masked facial regions which mainly include eyes, nose, mouth, lips, and skin to capture local and global aspects that in turn help in encoding generic and transferable features. Through a variety of experiments on diverse downstream tasks, we demonstrate MARLIN to be an excellent facial video encoder as well as feature extractor, that performs consistently well across a variety of downstream tasks including FAR (1.13% gain over supervised benchmark), FER (2.64% gain over unsupervised benchmark), DFD (1.86% gain over unsupervised benchmark), LS (29.36% gain for Frechet Inception Distance), and even in low data regime. Our code and models are available at https://github.com/ControlNet/MARLIN.

Most deepfake detection methods focus on detecting spatial and/or spatio-temporal changes in facial attributes and are centered around the binary classification task of detecting whether a video is real or fake. This is because available benchmark datasets contain mostly visual-only modifications present in the entirety of the video. However, a sophisticated deepfake may include small segments of audio or audio-visual manipulations that can completely change the meaning of the video content. To addresses this gap, we propose and benchmark a new dataset, Localized Audio Visual DeepFake (LAV-DF), consisting of strategic content-driven audio, visual and audio-visual manipulations. The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations. We further improve (i.e. BA-TFD+) the baseline method by replacing the backbone with a Multiscale Vision Transformer and guide the training process with contrastive, frame classification, boundary matching and multimodal boundary matching loss functions. The quantitative analysis demonstrates the superiority of BA-TFD+ on temporal forgery localization and deepfake detection tasks using several benchmark datasets including our newly proposed dataset. The dataset, models and code are available at https://github.com/ControlNet/LAV-DF.

The brief responses given by listeners in group conversations are known as backchannels rendering the task of backchannel detection an essential facet of group interaction analysis. Most of the current backchannel detection studies explore various audio-visual cues for individuals. However, analysing all group members is of utmost importance for backchannel detection, like any group interaction. This study uses a graph neural network to model group interaction through all members' implicit and explicit behaviours. The proposed method achieves the best and second best performance on agreement estimation and backchannel detection tasks, respectively, of the 2022 MultiMediate: Multi-modal Group Behaviour Analysis for Artificial Mediation challenge.

In this work we address the Next Speaker Prediction sub challenge of the ACM '21 MultiMediate Grand Challenge. This challenge poses the problem of turn taking prediction in physically situated multiparty interaction. Solving this problem is essential for enabling fluent real-time multiparty human-machine interaction. This problem is made more difficult by the need for a robust solution that can perform effectively across a wide variety of settings and contexts. Prior work has shown that current state-of-the-art methods rely on machine learning approaches that do not generalize well to new settings and feature distributions. To address this problem, we propose the use of group-level focus of visual attention as additional information. We show that a simple combination of group-level focus of visual attention features and publicly available audio-video synchronizer models is competitive with state-of-the-art methods fine-tuned for the challenge dataset.

An extensive body of research has examined how specific emotional expressions shape social perceptions and social decisions, yet recent scholarship in emotion research has raised questions about the validity of emotion as a construct. In this article, we contrast the value of measuring emotional expressions with the more general construct of expressivity (in the sense of conveying a thought or emotion through any nonverbal behavior) and develop models that can automatically extract perceived expressivity from videos. Although less extensive, a solid body of research has shown expressivity to be an important element when studying interpersonal perception, particularly in psychiatric contexts. Here we examine the role expressivity plays in predicting social perceptions and decisions in the context of a social dilemma. We show that perceivers use more than facial expressions when making judgments of expressivity and see these expressions as conveying thoughts as well as emotions (although facial expressions and emotional attributions explain most of the variance in these judgments). We next show that expressivity can be predicted with high accuracy using Lasso and random forests. Our analysis shows that features related to motion dynamics are particularly important for modeling these judgments. We also show that learned models of expressivity have value in recognizing important aspects of a social situation. First, we revisit a previously published finding which showed that smile intensity was associated with the unexpectedness of outcomes in social dilemmas; instead, we show that expressivity is a better predictor (and explanation) of this finding. Second, we provide preliminary evidence that expressivity is useful for identifying “moments of interest” in a video sequence.

Automatic multimodal acquisition and understanding of social signals is an essential building block for natural and effective human-machine collaboration and communication. This paper introduces OpenSense, a platform for real-time multimodal acquisition and recognition of social signals. OpenSense enables precisely synchronized and coordinated acquisition and processing of human behavioral signals. Powered by the Microsoft's Platform for Situated Intelligence, OpenSense supports a range of sensor devices and machine learning tools and encourages developers to add new components to the system through straightforward mechanisms for component integration. This platform also offers an intuitive graphical user interface to build application pipelines from existing components. OpenSense is freely available for academic research.

Motivational Interviewing (MI) is defined as a collaborative conversation style that evokes the client's own intrinsic reasons for behavioral change. In MI research, the clients' attitude (willingness or resistance) toward change as expressed through language, has been identified as an important indicator of their subsequent behavior change. Automated coding of these indicators provides systematic and efficient means for the analysis and assessment of MI therapy sessions. In this paper, we study and analyze behavioral cues in client language and speech that bear indications of the client's behavior toward change during a therapy session, using a database of dyadic motivational interviews between therapists and clients with alcohol-related problems. Deep language and voice encoders, \ie BERT and VGGish, trained on large amounts of data are used to extract features from each utterance. We develop a neural network to automatically detect the MI codes using both the clients' and therapists' language and clients' voice, and demonstrate the importance of semantic context in such detection. Additionally, we develop machine learning models for predicting alcohol-use behavioral outcomes of clients through language and voice analysis. Our analysis demonstrates that we are able to estimate MI codes using clients' textual utterances along with preceding textual context from both the therapist and client, reaching an F1-score of 0.72 for a speaker-independent three-class classification. We also report initial results for using the clients' data for predicting behavioral outcomes, which outlines the direction for future work.

We develop and evaluate models for automatic vision-based voice activity detection (VAD) in multiparty human-human interactions that are aimed at complementing acoustic VAD methods. We provide evidence that this type of vision-based VAD models are susceptible to spatial bias in the dataset used for their development; the physical settings of the interaction, usually constant throughout data acquisition, determines the distribution of head poses of the participants. Our results show that when the head pose distributions are significantly different in the train and test sets, the performance of the vision-based VAD models drops significantly. This suggests that previously reported results on datasets with a fixed physical configuration may overestimate the generalization capabilities of this type of models. We also propose a number of possible remedies to the spatial bias, including data augmentation, input masking and dynamic features, and provide an in-depth analysis of the visual cues used by the developed vision-based VAD models.

This paper presents our efforts towards building an architecture for digitally-mediated sign language communication. The architecture is based on a client-server model and enables a near real-time recognition of sign language signs on a mobile device. The paper describes the two main components of the architecture, a recognition engine (server-side) and a mobile application (client-side), and outlines directions for future work.

Self-disclosure to others has a proven benefit for one’s mental health. It is shown that disclosure to computers can be similarly beneficial for emotional and psychological well-being. In this paper, we analyzed verbal and nonverbal behavior associated with self-disclosure in two datasets containing structured human-human and human-agent interviews from more than 200 participants. Correlation analysis of verbal and nonverbal behavior revealed that linguistic features such as affective and cognitive content in verbal behavior, and nonverbal behavior such as head gestures are associated with intimate self-disclosure. A multimodal deep neural network was developed to automatically estimate the level of intimate self-disclosure from verbal and nonverbal behavior. Between modalities, verbal behavior was the best modality for estimating self-disclosure within-corpora achieving r = 0.66. However, the cross-corpus evaluation demonstrated that nonverbal behavior can outperform language modality in cross-corpus evaluation. Such automatic models can be deployed in interactive virtual agents or social robots to evaluate rapport and guide their conversational strategy.

Embodied interactive agents possessing emotional intelligence and empathy can create natural and engaging social interactions. Providing appropriate responses by interactive virtual agents requires the ability to perceive users’ emotional states. In this paper, we study and analyze behavioral cues that indicate an opportunity to provide an empathetic response. Emotional tone in language in addition to facial expressions are strong indicators of dramatic sentiment in conversation that warrant an empathetic response. To automatically recognize such instances, we develop a multimodal deep neural network for identifying opportunities when the agent should express positive or negative empathetic responses. We train and evaluate our model using audio, video and language from human-agent interactions in a wizard-of-Oz setting, using the wizard’s empathetic responses and annotations collected on Amazon Mechanical Turk as ground-truth labels. Our model outperforms a text-based baseline achieving F1-score of 0.71 on a three-class classification. We further investigate the results and evaluate the capability of such a model to be deployed for real-world human-agent interactions.

This study proposes, develops, and evaluates methods for modeling the eye-gaze direction and head orientation of a person in multiparty open-world dialogues, as a function of low-level communicative signals generated by his/hers interlocutors. These signals include speech activity, eye-gaze direction, and head orientation, all of which can be estimated in real time during the interaction. By utilizing these signals and novel data representations suitable for the task and context, the developed methods can generate plausible candidate gaze targets in real time. The methods are based on Feedforward Neural Networks and Long Short-Term Memory Networks. The proposed methods are developed using several hours of unrestricted interaction data and their performance is compared with a heuristic baseline method. The study offers an extensive evaluation of the proposed methods that investigates the contribution of different predictors to the accurate generation of candidate gaze targets. The results show that the methods can accurately generate candidate gaze targets when the person being modeled is in a listening state. However, when the person being modeled is in a speaking state, the proposed methods yield significantly lower performance.

We have developed an interactive virtual audience platform for public speaking training. Users' public speaking behavior is automatically analyzed using multimodal sensors, and ultimodal feedback is produced by virtual characters and generic visual widgets depending on the user's behavior. The flexibility of our system allows to compare different interaction mediums (e.g. virtual reality vs normal interaction), social situations (e.g. one-on-one meetings vs large audiences) and trained behaviors (e.g. general public speaking performance vs specific behaviors).

In this paper, we describe a project that explores a novel experimental setup towards building a spoken, multi-modally rich, and human-like multiparty tutoring robot. A human-robot interaction setup is designed, and a human-human dialogue corpus is collected. The corpus targets the development of a dialogue system platform to study verbal and nonverbal tutoring strategies in multiparty spoken interactions with robots which are capable of spoken dialogue. The dialogue task is centered on two participants involved in a dialogue aiming to solve a card-ordering game. Along with the participants sits a tutor (robot) that helps the participants perform the task, and organizes and balances their interaction. Different multimodal signals captured and auto-synchronized by different audio-visual capture technologies, such as a microphone array, Kinects, and video cameras, were coupled with manual annotations. These are used build a situated model of the interaction based on the participants personalities, their state of attention, their conversational engagement and verbal dominance, and how that is correlated with the verbal and visual feed-back, turn-management, and conversation regulatory actions generated by the tutor. Driven by the analysis of the corpus, we will show also the detailed design methodologies for an affective, and multimodally rich dialogue system that allows the robot to measure incrementally the attention states, and the dominance for each participant, allowing the robot head Furhat to maintain a well-coordinated, balanced, and engaging conversation, that attempts to maximize the agreement and the contribution to solve the task.

We will show in this demonstrator an advanced multimodal and multiparty spoken conversational system using Furhat, a robot head based on projected facial animation. Furhat is a human-like interface that utilizes facial animation for physical robot heads using back-projection. In the system, multimodality is enabled using speech and rich visual input signals such as multi-person real-time face tracking and microphone tracking. The demonstrator will showcase a system that is able to carry out social dialogue with multiple interlocutors simultaneously with rich output signals such as eye and head coordination, lips synchronized speech synthesis, and non-verbal facial gestures used to regulate fluent and expressive multiparty conversations.