arXiv subjects

Ramanathan Subramanian

Publications and source records attributed to Ramanathan Subramanian.

At least 19 recordsLinked to original sources

arXiv2025

CSGaze: Context-aware Social Gaze Prediction

A person's gaze offers valuable insights into their focus of attention, level of social engagement, and confidence. In this work, we investigate how contextual cues combined with visual scene and facial information can be effectively utilized to predict and interpret social gaze patterns during conversational interactions. We introduce CSGaze, a context aware multimodal approach that leverages facial, scene information as complementary inputs to enhance social gaze pattern prediction from multi-person images. The model also incorporates a fine-grained attention mechanism centered on the principal speaker, which helps in better modeling social gaze dynamics. Experimental results show that CSGaze performs competitively with state-of-the-art methods on GP-Static, UCO-LAEO and AVA-LAEO. Our findings highlight the role of contextual cues in improving social gaze prediction. Additionally, we provide initial explainability through generated attention scores, offering insights into the model's decision-making process. We also demonstrate our model's generalizability by testing our model on open set datasets that demonstrating its robustness across diverse scenarios.

cs.CV↗

arXiv2025

On the Validity of Head Motion Patterns as Generalisable Depression Biomarkers

Depression is a debilitating mood disorder negatively impacting millions worldwide. While researchers have explored multiple verbal and non-verbal behavioural cues for automated depression assessment, head motion has received little attention thus far. Further, the common practice of validating machine learning models via a single dataset can limit model generalisability. This work examines the effectiveness and generalisability of models utilising elementary head motion units, termed kinemes, for depression severity estimation. Specifically, we consider three depression datasets from different western cultures (German: AVEC2013, Australian: Blackdog and American: Pitt datasets) with varied contextual and recording settings to investigate the generalisability of the derived kineme patterns via two methods: (i) k-fold cross-validation over individual/multiple datasets, and (ii) model reuse on other datasets. Evaluating classification and regression performance with classical machine learning methods, our results show that: (1) head motion patterns are efficient biomarkers for estimating depression severity, achieving highly competitive performance for both classification and regression tasks on a variety of datasets, including achieving the second best Mean Absolute Error (MAE) on the AVEC2013 dataset, and (2) kineme-based features are more generalisable than (a) raw head motion descriptors for binary severity classification, and (b) other visual behavioural cues for severity estimation (regression).

cs.LG↗

arXiv2025

EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cues

We present EditIQ, a completely automated framework for cinematically editing scenes captured via a stationary, large field-of-view and high-resolution camera. From the static camera feed, EditIQ initially generates multiple virtual feeds, emulating a team of cameramen. These virtual camera shots termed rushes are subsequently assembled using an automated editing algorithm, whose objective is to present the viewer with the most vivid scene content. To understand key scene elements and guide the editing process, we employ a two-pronged approach: (1) a large language model (LLM)-based dialogue understanding module to analyze conversational flow, coupled with (2) visual saliency prediction to identify meaningful scene elements and camera shots therefrom. We then formulate cinematic video editing as an energy minimization problem over shot selection, where cinematic constraints determine shot choices, transitions, and continuity. EditIQ synthesizes an aesthetically and visually compelling representation of the original narrative while maintaining cinematic coherence and a smooth viewing experience. Efficacy of EditIQ against competing baselines is demonstrated via a psychophysical study involving twenty participants on the BBC Old School dataset plus eleven theatre performance videos. Video samples from EditIQ can be found at https://editiq-ave.github.io/.

cs.MM↗

arXiv2024

MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding

Estimating the Most Important Person (MIP) in any social event setup is a challenging problem mainly due to contextual complexity and scarcity of labeled data. Moreover, the causality aspects of MIP estimation are quite subjective and diverse. To this end, we aim to address the problem by annotating a large-scale `in-the-wild' dataset for identifying human perceptions about the `Most Important Person (MIP)' in an image. The paper provides a thorough description of our proposed Multimodal Large Language Model (MLLM) based data annotation strategy, and a thorough data quality analysis. Further, we perform a comprehensive benchmarking of the proposed dataset utilizing state-of-the-art MIP localization methods, indicating a significant drop in performance compared to existing datasets. The performance drop shows that the existing MIP localization algorithms must be more robust with respect to `in-the-wild' situations. We believe the proposed dataset will play a vital role in building the next-generation social situation understanding methods. The code and data is available at https://github.com/surbhimadan92/MIP-GAF.

cs.CV↗

arXiv2024

Mood as a Contextual Cue for Improved Emotion Inference

Psychological studies observe that emotions are rarely expressed in isolation and are typically influenced by the surrounding context. While recent studies effectively harness uni- and multimodal cues for emotion inference, hardly any study has considered the effect of long-term affect, or \emph{mood}, on short-term \emph{emotion} inference. This study (a) proposes time-continuous \emph{valence} prediction from videos, fusing multimodal cues including \emph{mood} and \emph{emotion-change} ($Δ$) labels, (b) serially integrates spatial and channel attention for improved inference, and (c) demonstrates algorithmic generalisability with experiments on the \emph{EMMA} and \emph{AffWild2} datasets. Empirical results affirm that utilising mood labels is highly beneficial for dynamic valence prediction. Comparing \emph{unimodal} (training only with mood labels) vs \emph{multimodal} (training with mood and $Δ$ labels) results, inference performance improves for the latter, conveying that both long and short-term contextual cues are critical for time-continuous emotion inference.

cs.HC↗

arXiv2024

EEG-based Cognitive Load Estimation of Acoustic Parameters for Data Sonification

Sonification is a data visualization technique which expresses data attributes via psychoacoustic parameters, which are non-speech audio signals used to convey information. This paper investigates the binary estimation of cognitive load induced by psychoacoustic parameters conveying the focus level of an astronomical image via Electroencephalogram (EEG) embeddings. Employing machine learning and deep learning methodologies, we demonstrate that EEG signals are reliable for (a) binary estimation of cognitive load, (b) isolating easy vs difficult visual-to-auditory perceptual mappings, and (c) capturing perceptual similarities among psychoacoustic parameters. Our key findings reveal that (1) EEG embeddings can reliably measure cognitive load, achieving a peak F1-score of 0.98; (2) Extreme focus levels are easier to detect via auditory mappings than intermediate ones, and (3) psychoacoustic parameters inducing comparable cognitive load levels tend to generate similar EEG encodings.

cs.HC↗

arXiv2023

MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings

Bodily behavioral language is an important social cue, and its automated analysis helps in enhancing the understanding of artificial intelligence systems. Furthermore, behavioral language cues are essential for active engagement in social agent-based user interactions. Despite the progress made in computer vision for tasks like head and body pose estimation, there is still a need to explore the detection of finer behaviors such as gesturing, grooming, or fumbling. This paper proposes a multiview attention fusion method named MAGIC-TBR that combines features extracted from videos and their corresponding Discrete Cosine Transform coefficients via a transformer-based approach. The experiments are conducted on the BBSI dataset and the results demonstrate the effectiveness of the proposed feature fusion with multiview attention. The code is available at: https://github.com/surbhimadan92/MAGIC-TBR

cs.CV↗

arXiv2023

A Weakly Supervised Approach to Emotion-change Prediction and Improved Mood Inference

Whilst a majority of affective computing research focuses on inferring emotions, examining mood or understanding the \textit{mood-emotion interplay} has received significantly less attention. Building on prior work, we (a) deduce and incorporate emotion-change ($Δ$) information for inferring mood, without resorting to annotated labels, and (b) attempt mood prediction for long duration video clips, in alignment with the characterisation of mood. We generate the emotion-change ($Δ$) labels via metric learning from a pre-trained Siamese Network, and use these in addition to mood labels for mood classification. Experiments evaluating \textit{unimodal} (training only using mood labels) vs \textit{multimodal} (training using mood plus $Δ$ labels) models show that mood prediction benefits from the incorporation of emotion-change information, emphasising the importance of modelling the mood-emotion interplay for effective mood inference.

cs.HC↗

arXiv2023

Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning

Whilst deep learning techniques have achieved excellent emotion prediction, they still require large amounts of labelled training data, which are (a) onerous and tedious to compile, and (b) prone to errors and biases. We propose Multi-Task Contrastive Learning for Affect Representation (\textbf{MT-CLAR}) for few-shot affect inference. MT-CLAR combines multi-task learning with a Siamese network trained via contrastive learning to infer from a pair of expressive facial images (a) the (dis)similarity between the facial expressions, and (b) the difference in valence and arousal levels of the two faces. We further extend the image-based MT-CLAR framework for automated video labelling where, given one or a few labelled video frames (termed \textit{support-set}), MT-CLAR labels the remainder of the video for valence and arousal. Experiments are performed on the AFEW-VA dataset with multiple support-set configurations; moreover, supervised learning on representations learnt via MT-CLAR are used for valence, arousal and categorical emotion prediction on the AffectNet and AFEW-VA datasets. The results show that valence and arousal predictions via MT-CLAR are very comparable to the state-of-the-art (SOTA), and we significantly outperform SOTA with a support-set $\approx$6\% the size of the video dataset.

cs.CV↗

arXiv2023

A Virtual Reality Game to Improve Physical and Cognitive Acuity

We present the Virtual Human Benchmark (VHB) game to evaluate and improve physical and cognitive acuity. VHB simulates in 3D the BATAK lightboard game, which is designed to improve physical reaction and hand-eye coordination, on the \textit{Oculus Rift} and \textit{Quest} headsets. The game comprises the \textit{reaction}, \textit{accumulator} and \textit{sequence} modes; \bj{along} with the \textit{reaction} and \textit{accumulator} modes which mimic BATAK functionalities, the \textit{sequence} mode involves the user repeating a sequence of illuminated targets with increasing complexity to train visual memory and cognitive processing. A first version of the game (VHB v1) was evaluated against the real-world BATAK by 20 users, and their feedback was utilized to improve game design and obtain a second version (VHB v2). Another study to evaluate VHB v2 was conducted with 20 users, whose results confirmed that the deign improvements enhanced game usability and user experience in multiple respects. Also, logging and visualization of performance data such as \textit{reaction time}, \textit{speed between targets} and \textit{completed sequence patterns} provides useful data for coaches/therapists monitoring sports/rehabilitation regimens.

cs.HC↗

arXiv2023

Explainable Depression Detection via Head Motion Patterns

While depression has been studied via multimodal non-verbal behavioural cues, head motion behaviour has not received much attention as a biomarker. This study demonstrates the utility of fundamental head-motion units, termed \emph{kinemes}, for depression detection by adopting two distinct approaches, and employing distinctive features: (a) discovering kinemes from head motion data corresponding to both depressed patients and healthy controls, and (b) learning kineme patterns only from healthy controls, and computing statistics derived from reconstruction errors for both the patient and control classes. Employing machine learning methods, we evaluate depression classification performance on the \emph{BlackDog} and \emph{AVEC2013} datasets. Our findings indicate that: (1) head motion patterns are effective biomarkers for detecting depressive symptoms, and (2) explanatory kineme patterns consistent with prior findings can be observed for the two classes. Overall, we achieve peak F1 scores of 0.79 and 0.82, respectively, over BlackDog and AVEC2013 for binary classification over episodic \emph{thin-slices}, and a peak F1 of 0.72 over videos for AVEC2013.

cs.CV↗

arXiv2023

Focus on Change: Mood Prediction by Learning Emotion Changes via Spatio-Temporal Attention

While emotion and mood interchangeably used, they differ in terms of duration, intensity and attributes. Even as multiple psychology studies examine the mood-emotion relationship, mood prediction has barely been studied. Recent machine learning advances such as the attention mechanism to focus on salient parts of the input data, have only been applied to infer emotions rather than mood. We perform mood prediction by incorporating both mood and emotion change information. We additionally explore spatial and temporal attention, and parallel/sequential arrangements of the spatial and temporal attention modules to improve mood prediction performance. To examine generalizability of the proposed method, we evaluate models trained on the AFEW dataset with EMMA. Experiments reveal that (a) emotion change information is inherently beneficial to mood prediction, and (b) prediction performance improves with the integration of sequential and parallel spatial-temporal attention modules.

cs.HC↗

arXiv2023

Explainable Human-centered Traits from Head Motion and Facial Expression Dynamics

We explore the efficacy of multimodal behavioral cues for explainable prediction of personality and interview-specific traits. We utilize elementary head-motion units named kinemes, atomic facial movements termed action units and speech features to estimate these human-centered traits. Empirical results confirm that kinemes and action units enable discovery of multiple trait-specific behaviors while also enabling explainability in support of the predictions. For fusing cues, we explore decision and feature-level fusion, and an additive attention-based fusion strategy which quantifies the relative importance of the three modalities for trait prediction. Examining various long-short term memory (LSTM) architectures for classification and regression on the MIT Interview and First Impressions Candidate Screening (FICS) datasets, we note that: (1) Multimodal approaches outperform unimodal counterparts; (2) Efficient trait predictions and plausible explanations are achieved with both unimodal and multimodal approaches, and (3) Following the thin-slice approach, effective trait prediction is achieved even from two-second behavioral snippets.

cs.LG↗

arXiv2022

To Improve Is to Change: Towards Improving Mood Prediction by Learning Changes in Emotion

Although the terms mood and emotion are closely related and often used interchangeably, they are distinguished based on their duration, intensity and attribution. To date, hardly any computational models have (a) examined mood recognition, and (b) modelled the interplay between mood and emotional state in their analysis. In this paper, as a first step towards mood prediction, we propose a framework that utilises both dominant emotion (or mood) labels, and emotional change labels on the AFEW-VA database. Experiments evaluating unimodal (trained only using mood labels) and multimodal (trained with both mood and emotion change labels) convolutional neural networks confirm that incorporating emotional change information in the network training process can significantly improve the mood prediction performance, thus highlighting the importance of modelling emotion and mood simultaneously for improved performance in affective state recognition.

cs.HC↗

arXiv2022

Neural Encoding of Songs is Modulated by Their Enjoyment

We examine user and song identification from neural (EEG) signals. Owing to perceptual subjectivity in human-media interaction, music identification from brain signals is a challenging task. We demonstrate that subjective differences in music perception aid user identification, but hinder song identification. In an attempt to address intrinsic complexities in music identification, we provide empirical evidence on the role of enjoyment in song recognition. Our findings reveal that considering song enjoyment as an additional factor can improve EEG-based song recognition.

cs.HC↗

arXiv2022

Affective Computational Advertising Based on Perceptual Metrics

We present \textbf{ACAD}, an \textbf{a}ffective \textbf{c}omputational \textbf{ad}vertising framework expressly derived from perceptual metrics. Different from advertising methods which either ignore the emotional nature of (most) programs and ads, or are based on axiomatic rules, the ACAD formulation incorporates findings from a user study examining the effect of within-program ad placements on ad perception. A linear program formulation seeking to achieve (a) \emph{genuine} ad assessments and (b) \emph{maximal} ad recall is then proposed. Effectiveness of the ACAD framework is confirmed via a validational user study, where ACAD-induced ad placements are found to be optimal with respect to objectives (a) and (b) against competing approaches.

cs.HC↗

arXiv2022

Outlier-based Autism Detection using Longitudinal Structural MRI

Diagnosis of Autism Spectrum Disorder (ASD) using clinical evaluation (cognitive tests) is challenging due to wide variations amongst individuals. Since no effective treatment exists, prompt and reliable ASD diagnosis can enable the effective preparation of treatment regimens. This paper proposes structural Magnetic Resonance Imaging (sMRI)-based ASD diagnosis via an outlier detection approach. To learn Spatio-temporal patterns in structural brain connectivity, a Generative Adversarial Network (GAN) is trained exclusively with sMRI scans of healthy subjects. Given a stack of three adjacent slices as input, the GAN generator reconstructs the next three adjacent slices; the GAN discriminator then identifies ASD sMRI scan reconstructions as outliers. This model is compared against two other baselines -- a simpler UNet and a sophisticated Self-Attention GAN. Axial, Coronal, and Sagittal sMRI slices from the multi-site ABIDE II dataset are used for evaluation. Extensive experiments reveal that our ASD detection framework performs comparably with the state-of-the-art with far fewer training data. Furthermore, longitudinal data (two scans per subject over time) achieve 17-28% higher accuracy than cross-sectional data (one scan per subject). Among other findings, metrics employed for model training as well as reconstruction loss computation impact detection performance, and the coronal modality is found to best encode structural information for ASD detection.

eess.IV↗

arXiv2022

Automated Parkinson's Disease Detection and Affective Analysis from Emotional EEG Signals

While Parkinson's disease (PD) is typically characterized by motor disorder, there is evidence of diminished emotion perception in PD patients. This study examines the utility of affective Electroencephalography (EEG) signals to understand emotional differences between PD vs Healthy Controls (HC), and for automated PD detection. Employing traditional machine learning and deep learning methods, we explore (a) dimensional and categorical emotion recognition, and (b) PD vs HC classification from emotional EEG signals. Our results reveal that PD patients comprehend arousal better than valence, and amongst emotion categories, \textit{fear}, \textit{disgust} and \textit{surprise} less accurately, and \textit{sadness} most accurately. Mislabeling analyses confirm confounds among opposite-valence emotions with PD data. Emotional EEG responses also achieve near-perfect PD vs HC recognition. {Cumulatively, our study demonstrates that (a) examining \textit{implicit} responses alone enables (i) discovery of valence-related impairments in PD patients, and (ii) differentiation of PD from HC, and (b) emotional EEG analysis is an ecologically-valid, effective, facile and sustainable tool for PD diagnosis vis-á-vis self reports, expert assessments and resting-state analysis.}

eess.SP↗