Related papers: METEOR: Learning Memory and Time Efficient Represe…

Latent space models are widely used for analyzing high-dimensional discrete data matrices, such as patient-feature matrices in electronic health records (EHRs), by capturing complex dependence structures through low-dimensional embeddings.…

For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…

Unmanned surface vehicles can encounter a number of varied visual circumstances during operation, some of which can be very difficult to interpret. While most cases can be solved only using color camera images, some weather and lighting…

We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic…

Real-time analytics and decision-making require online anomaly detection (OAD) to handle drifts in data streams efficiently and effectively. Unfortunately, existing approaches are often constrained by their limited detection capacity and…

Sequential recommendation (SR) systems excel at capturing users' dynamic preferences by leveraging their interaction histories. Most existing SR systems assign a single embedding vector to each item to represent its features, adopting…

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come…

Multimodal large language models (MLLMs) have demonstrated strong performance in understanding videos holistically, yet their ability to process streaming videos-videos are treated as a sequence of visual events-remains underexplored.…

Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for applications such as telepresence, augmented reality, and remote sensing. Recent…

Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…

Weather prediction is a quintessential problem involving the forecasting of a complex, nonlinear, and chaotic high-dimensional dynamical system. This work introduces an efficient reduced-order modeling (ROM) framework for short-range…

There has been an explosion of multimodal content generated on social media networks in the last few years, which has necessitated a deeper understanding of social media content and user behavior. We present a novel content-independent…

Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…

Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis. From a behavioral…

Substantial advances in multi-modal Artificial Intelligence (AI) facilitate the combination of diverse medical modalities to achieve holistic health assessments. We present COMPRER , a novel multi-modal, multi-objective pretraining…

Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities are available in training and…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…

Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this…

Multimodal representation learning has demonstrated remarkable potential in enabling models to process and integrate diverse data modalities, such as text and images, for improved understanding and performance. While the medical domain can…