Related papers: Dyadic Neural Dynamics: Extending Representation L…
Self-supervised learning has produced impressive results in multimedia domains of audio, vision and speech. This paradigm is equally, if not more, relevant for the domain of biosignals, owing to the scarcity of labelled data in such…
Signed networks allow us to model conflicting relationships and interactions, such as friend/enemy and support/oppose. These signed interactions happen in real-time. Modeling such dynamics of signed networks is crucial to understanding the…
Mirror neurons are a class of neurons that activate both when an individual observes an action and when they perform the same action. This mechanism reveals a fundamental interplay between action understanding and embodied execution,…
Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by challenges in social communication, repetitive behavior, and sensory processing. One important research area in ASD is evaluating children's behavioral…
Machine learning techniques have enabled researchers to leverage neuroimaging data to decode speech from brain activity, with some amazing recent successes achieved by applications built using invasive devices. However, research requiring…
Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive…
Modern online platforms offer users an opportunity to participate in a variety of content-creation, social networking, and shopping activities. With the rapid proliferation of such online services, learning data-driven user behavior models…
Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-to-many relationship, as identical visual inputs reliably…
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with…
Compositionality in knowledge and language--the ability to represent complex concepts as a combination of simpler ones--is a hallmark of human cognition and communication. Despite recent advances, deep neural networks still struggle to…
We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion. We combine the motion and…
Motivated by the challenge of seamless cross-dataset transfer in EEG signal processing, this article presents an exploratory study on the use of Joint Embedding Predictive Architectures (JEPAs). In recent years, self-supervised learning has…
A common view on the brain learning processes proposes that the three classic learning paradigms -- unsupervised, reinforcement, and supervised -- take place in respectively the cortex, the basal-ganglia, and the cerebellum. However,…
The Platonic Representation Hypothesis suggests a universal, modality-independent reality representation behind different data modalities. Inspired by this, we view each neuron as a system and detect its multi-segment activity data under…
Understanding and decoding brain activity from electroencephalography (EEG) signals is a fundamental challenge in neuroscience and AI, with applications in cognition, emotion recognition, diagnosis, and brain-computer interfaces. While…
With the rapid development in artificial intelligence, social computing has evolved beyond social informatics toward the birth of social intelligence systems. This paper, therefore, takes initiatives to propose a social behaviour…
Characterizing interactions between brain areas is a fundamental goal of systems neuroscience. While such analyses are possible when areas are recorded simultaneously, it is rare to observe all combinations of areas of interest within a…
This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynamics, and their blending induces intractable complexity in the…
Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining…
Human emotion is expressed in many communication modalities and media formats and so their computational study is equally diversified into natural language processing, audio signal analysis, computer vision, etc. Similarly, the large…