Related papers: MVCNet: Multiview Contrastive Network for Unsuperv…

Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However,…

Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks. Real-world networks are usually with multiplex or having multi-view representations from different relations. Recently, there has…

Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural…

State-of-the-art deep learning approaches for skin lesion recognition often require pretraining on larger and more varied datasets, to overcome the generalization limitations derived from the reduced size of the skin lesion imaging…

This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on…

There have been recent efforts to learn more meaningful representations via fixed length codewords from mesh data, since a mesh serves as a complete model of underlying 3D shape compared to a point cloud. However, the mesh connectivity…

Due to the inter- and intra- variation of respiratory motion, it is highly desired to provide real-time volumetric images during the treatment delivery of lung stereotactic body radiation therapy (SBRT) for accurate and active motion…

In recent studies on MRI reconstruction, advances have shown significant promise for further accelerating the MRI acquisition. Most state-of-the-art methods require a large amount of fully-sampled data to optimise reconstruction models,…

Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image. Previous works assume missing region patterns are known, limiting its application scope. In this paper, we relax…

Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a…

In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge…

Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful…

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…

Deep Learning (DL) and specifically CNN models have become a de facto method for a wide range of vision tasks, outperforming traditional machine learning (ML) methods. Consequently, they drew a lot of attention in the neuroimaging field in…

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well…

The ability to decompose scenes into their object components is a desired property for autonomous agents, allowing them to reason and act in their surroundings. Recently, different methods have been proposed to learn object-centric…

Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works…

Simultaneous object recognition and pose estimation are two key functionalities for robots to safely interact with humans as well as environments. Although both object recognition and pose estimation use visual input, most state-of-the-art…

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire network. This process can…

Reconstruction of 3D open surfaces (e.g., non-watertight meshes) is an underexplored area of computer vision. Recent learning-based implicit techniques have removed previous barriers by enabling reconstruction in arbitrary resolutions. Yet,…