Related papers: TempoFormer: A Transformer for Temporally-aware Re…

We present two deep learning approaches to narrative text understanding for character relationship modelling. The temporal evolution of these relations is described by dynamic word embeddings, that are designed to learn semantic changes…

Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic,…

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Multi-agent trajectory prediction is a fundamental problem in autonomous driving. The key challenges in prediction are accurately anticipating the behavior of surrounding agents and understanding the scene context. To address these…

Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively…

Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field…

Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconstrained. Under extreme sparsity, multiple physically plausible fields may remain consistent…

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

The growing interest in Temporal Graph Neural Networks (TGNNs) stems from their ability to model complex dynamics and deliver superior performance. However, TGNNs encounter fundamental challenges in capturing long-term dependencies and…

Time series forecasts are often influenced by exogenous contextual features in addition to their corresponding history. For example, in financial settings, it is hard to accurately predict a stock price without considering public sentiments…

Language is an interface to the outside world. In order for embodied agents to use it, language must be grounded in other, sensorimotor modalities. While there is an extended literature studying how machines can learn grounded language, the…

Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video…

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Vision-language-action models have gained significant attention for their ability to model multimodal sequences in embodied instruction following tasks. However, most existing models rely on causal attention, which we find suboptimal for…

Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious…

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…

Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…

Many of language models' impressive capabilities originate from their in-context learning: based on instructions or examples, they can infer and perform new tasks without weight updates. In this work, we investigate when representations for…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…