Related papers: FlowFormer: A Transformer Architecture and Its Mas…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denoising. Non-overlapping window-based self-attention is used in…

This research presents a novel depth estimation algorithm based on a Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset. This research adopts a transformer model, initially renowned for its success in natural…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Image Captioning is an important Language and Vision task that finds application in a variety of contexts, ranging from healthcare to autonomous vehicles. As many real-world applications rely on devices with limited resources, much effort…

Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scalability and practical deployment. We introduce…

Learning-based fluid simulation networks have been proven as viable alternatives to traditional numerical solvers for the Navier-Stokes equations. Existing neural methods follow Smoothed Particle Hydrodynamics (SPH) frameworks, which…

Segmenting thin structures like infrastructure cracks and anatomical vessels is a task hampered by topology-sensitive geometry, high annotation costs, and poor generalization across domains. Existing methods address these challenges in…

Fluence map prediction is central to automated radiotherapy planning but remains an ill-posed inverse problem due to the complex relationship between volumetric anatomy and beam-intensity modulation. Convolutional methods in prior work…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

Vision-language models (VLMs) have been widely applied to 2D medical image analysis due to their ability to align visual and textual representations. However, extending VLMs to 3D imaging remains computationally challenging. Existing 3D…

Endovascular navigation is a crucial aspect of minimally invasive procedures, where precise control of curvilinear instruments like guidewires is critical for successful interventions. A key challenge in this task is accurately predicting…

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection. Nevertheless, their real-time deployment on edge platforms remains constrained by decoder…

Event cameras provide high temporal precision, low data rates, and high dynamic range visual perception, which are well-suited for optical flow estimation. While data-driven optical flow estimation has obtained great success in RGB cameras,…

We propose a flow-guided transformer, which innovatively leverage the motion discrepancy exposed by optical flows to instruct the attention retrieval in transformer for high fidelity video inpainting. More specially, we design a novel flow…

Objective: To achieve accurate 3-D reconstruction and quantitative analysis of human retinal vasculature from a single optical coherence tomography angiography (OCTA) scan. Methods: We introduce Freqformer, a novel Transformer-based model…

While deep learning-based models like transformers, have revolutionized time-series and vision tasks, they remain highly susceptible to noise and often overfit on noisy patterns rather than robust features. This issue is exacerbated in…

The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in…