Related papers: OptFormer: Optical Flow-Guided Attention and Phase…

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher…

The increasing frequency and severity of climate related disasters have intensified the need for real time monitoring, early warning, and informed decision-making. Earth Observation (EO), powered by satellite data and Machine Learning (ML),…

Recent Few-Shot Learning (FSL) methods put emphasis on generating a discriminative embedding features to precisely measure the similarity between support and query sets. Current CNN-based cross-attention approaches generate discriminative…

Despite the Transformer's dominance across machine learning, its architecture remains largely heuristic and lacks a unified theoretical foundation. We introduce Score-based Variational Flow (SVFlow), a continuous-time dynamical system for…

Accurate perception of the dynamic environment is a fundamental task for autonomous driving and robot systems. This paper introduces Let Occ Flow, the first self-supervised work for joint 3D occupancy and occupancy flow prediction using…

The Transformer model has shown strong performance in multivariate time series forecasting by leveraging channel-wise self-attention. However, this approach lacks temporal constraints when computing temporal features and does not utilize…

Video prediction yields future frames by employing the historical frames and has exhibited its great potential in many applications, e.g., meteorological prediction, and autonomous driving. Previous works often decode the ultimate…

Numerical Weather Prediction (NWP) system is an infrastructure that exerts considerable impacts on modern society.Traditional NWP system, however, resolves it by solving complex partial differential equations with a huge computing cluster,…

We present a new architecture for human action forecasting from videos. A temporal recurrent encoder captures temporal information of input videos while a self-attention model is used to attend on relevant feature dimensions of the input…

Making predictions of future frames is a critical challenge in autonomous driving research. Most of the existing methods for video prediction attempt to generate future frames in simple and fixed scenes. In this paper, we propose a novel…

This paper proposes CTP, a novel deep learning framework that integrates convolutional neural network(CNN), Transformer architectures, and physics-informed neural network(PINN) for ocean front prediction. Ocean fronts, as dynamic interfaces…

We introduce VistaFormer, a lightweight Transformer-based model architecture for the semantic segmentation of remote-sensing images. This model uses a multi-scale Transformer-based encoder with a lightweight decoder that aggregates global…

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…

Endowing visual agents with predictive capability is a key step towards video intelligence at scale. The predominant modeling paradigm for this is sequence learning, mostly implemented through LSTMs. Feed-forward Transformer architectures…

Optical coherence tomography (OCT) helps ophthalmologists assess macular edema, accumulation of fluids, and lesions at microscopic resolution. Quantification of retinal fluids is necessary for OCT-guided treatment management, which relies…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attention mitigates this by approximating attention with kernel…

As the impact of climate change escalates, the global necessity to transition to sustainable energy sources becomes increasingly evident. Renewable energies have emerged as a viable solution for users, with Photovoltaic energy being a…

This paper presents \textit{TopoFormer}, a novel hybrid deep learning architecture that integrates transformer-based encoders with convolutional long short-term memory (ConvLSTM) layers for the precise prediction of topographic beach…

State Space Models (SSMs) have recently gained traction in remote sensing change detection (CD) for their favorable scaling properties. In this paper, we explore the potential of modern convolutional and attention-based architectures as a…