English
Related papers

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

200 papers

Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by…

Image and Video Processing · Electrical Eng. & Systems 2021-10-12 Ali Hatamizadeh , Yucheng Tang , Vishwesh Nath , Dong Yang , Andriy Myronenko , Bennett Landman , Holger Roth , Daguang Xu

Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Sucheng Ren , Qihang Yu , Ju He , Xiaohui Shen , Alan Yuille , Liang-Chieh Chen

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance…

Image and Video Processing · Electrical Eng. & Systems 2023-10-20 Dayang Wang , Yongshun Xu , Shuo Han , Zhan Wu , Li Zhou , Bahareh Morovati , Hengyong Yu

Recent advances in end-to-end autonomous driving leverage multi-view images to construct BEV representations for motion planning. In motion planning, autonomous vehicles need considering both hard constraints imposed by geometrically…

Text-driven video editing aims to modify video content based on natural language instructions. While recent training-free methods have leveraged pretrained diffusion models, they often rely on an inversion-editing paradigm. This paradigm…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Guangzhao Li , Yanming Yang , Chenxi Song , Chi Zhang

We present Wave-Former, a novel method capable of high-accuracy 3D shape reconstruction for completely occluded, diverse, everyday objects. This capability can open new applications spanning robotics, augmented reality, and logistics. Our…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Laura Dodds , Maisy Lam , Waleed Akbar , Yibo Cheng , Fadel Adib

Auto-regressive neural sequence models have been shown to be effective across text generation tasks. However, their left-to-right decoding order prevents generation from being parallelized. Insertion Transformer (Stern et al., 2019) is an…

Computation and Language · Computer Science 2023-02-01 Zhisong Zhang , Yizhe Zhang , Bill Dolan

The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to quadratic time and memory…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Pourya Shamsolmoali , Masoumeh Zareapoor , Eric Granger , Michael Felsberg

Predicting molecular conformations (or 3D structures) from molecular graphs is a fundamental problem in many applications. Most existing approaches are usually divided into two steps by first predicting the distances between atoms and then…

Machine Learning · Computer Science 2025-01-07 Minkai Xu , Wujie Wang , Shitong Luo , Chence Shi , Yoshua Bengio , Rafael Gomez-Bombarelli , Jian Tang

Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Lingtong Kong , Chunhua Shen , Jie Yang

Despite rapid improvements in the performance of central processing unit (CPU), the calculation cost of simulating chemically reacting flow using CFD remains infeasible in many cases. The application of the convolutional neural networks…

Machine Learning · Computer Science 2023-07-26 Joongoo Jeon , Juhyeong Lee , Sung Joong Kim

We present the Fourier-Invertible Neural Encoder (FINE), a compact and interpretable architecture for dimension reduction in translation-equivariant datasets. FINE integrates reversible filters and monotonic activation functions with a…

Machine Learning · Computer Science 2025-12-02 Anqiao Ouyang , Hongyi Ke , Qi Wang

Facial Action Units (AU) is a vital concept in the realm of affective computing, and AU detection has always been a hot research topic. Existing methods suffer from overfitting issues due to the utilization of a large number of learnable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Kaishen Yuan , Zitong Yu , Xin Liu , Weicheng Xie , Huanjing Yue , Jingyu Yang

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semantic dependencies.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Jiashu Liao , Pietro Liò , Marc de Kamps , Duygu Sarikaya

While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares…

Computer Vision and Pattern Recognition · Computer Science 2022-04-13 Qiang Chen , Qiman Wu , Jian Wang , Qinghao Hu , Tao Hu , Errui Ding , Jian Cheng , Jingdong Wang

Monocular depth estimation (MDE) has attracted increasing interest in the past few years, owing to its important role in 3D vision. MDE is the estimation of a depth map from a monocular image/video to represent the 3D structure of a scene,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Shuai Li , Huibin Bai , Yanbo Gao , Chong Lv , Hui Yuan , Chuankun Li , Wei Hua , Tian Xie

In this work we propose a novel block preconditioner, labelled Explicit Decoupling Factor Approximation (EDFA), to accelerate the convergence of Krylov subspace solvers used to address the sequence of non-symmetric systems of linear…

Numerical Analysis · Mathematics 2021-07-07 Stefano Nardean , Massimiliano Ferronato , Ahmad S. Abushaikha

Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yicheng Liu , Shiduo Zhang , Zibin Dong , Baijun Ye , Tianyuan Yuan , Xiaopeng Yu , Linqi Yin , Chenhao Lu , Junhao Shi , Luca Jiang-Tao Yu , Liangtao Zheng , Tao Jiang , Jingjing Gong , Xipeng Qiu , Hang Zhao

In recent years, many deep learning-based methods have been proposed to tackle the problem of optical flow estimation and achieved promising results. However, they hardly consider that most videos are compressed and thus ignore the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Shili Zhou , Xuhao Jiang , Weimin Tan , Ruian He , Bo Yan

We present a new data-driven model to reconstruct nonlinear flow from spatially sparse observations. The model is a version of a conditional variational auto-encoder (CVAE), which allows for probabilistic reconstruction and thus uncertainty…

Machine Learning · Statistics 2021-02-24 Kristian Gundersen , Anna Oleynik , Nello Blaser , Guttorm Alendal