Related papers: Multi-Level Embedding and Alignment Network with C…
We propose to use deep convolutional neural networks to address the problem of cross-view image geolocalization, in which the geolocation of a ground-level query image is estimated by matching to georeferenced aerial images. We use…
Accelerated Cardiovascular Magnetic Resonance (CMR) image reconstruction remains a critical challenge due to the trade-off between scan time and image quality, particularly when generalizing across diverse acquisition settings. We propose…
Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images. However, most existing methods heavily rely on strictly pre-paired drone-satellite images for…
Multi-view depth estimation methods typically require the computation of a multi-view cost-volume, which leads to huge memory consumption and slow inference. Furthermore, multi-view matching can fail for texture-less surfaces, reflective…
We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout metric via neural graph matching, using an attention-based…
Cross-view geolocalization identifies the geographic location of street view images by matching them with a georeferenced satellite database. Significant challenges arise due to the drastic appearance and geometry differences between views.…
Anomalous crack region detection is a typical binary semantic segmentation task, which aims to detect pixels representing cracks on pavement surface images automatically by algorithms. Although existing deep learning-based methods have…
Cross-view geo-localization (CVGL) plays a vital role in drone-based multimedia applications, enabling precise localization by matching drone-captured aerial images against geo-tagged satellite databases in GNSS-denied environments.…
This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval. Most existing deep metric learning methods learn an embedding space with a general objective of increasing interclass distances and…
Multi-view anomaly detection aims to identify surface defects on complex objects using observations captured from multiple viewpoints. However, existing unsupervised methods often suffer from feature inconsistency arising from viewpoint…
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…
Training convolutional neural networks (CNNs) on high-resolution images is often bottlenecked by the cost of evaluating gradients of the loss on the finest spatial mesh. To address this, we propose Multiscale Gradient Estimation (MGE), a…
Real-world social networks and digital platforms are comprised of individuals (nodes) that are linked to other individuals or entities through multiple types of relationships (links). Sub-networks of such a network based on each type of…
In multi-person pose estimation, the left/right joint type discrimination is always a hard problem because of the similar appearance. Traditionally, we solve this problem by stacking multiple refinement modules to increase network's…
Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including…
Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet, current methods including aggregation-based and…
Compressive sensing (CS) is widely used to reduce the acquisition time of magnetic resonance imaging (MRI). Although state-of-the-art deep learning based methods have been able to obtain fast, high-quality reconstruction of CS-MR images,…
While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over complex narratives remains poorly evaluated. Existing summarization benchmarks fragment…
Traditional change detection methods usually follow the image differencing, change feature extraction and classification framework, and their performance is limited by such simple image domain differencing and also the hand-crafted…
In this paper, we present MLEANN (Meta-Learning Evolutionary Artificial Neural Network), an automatic computational framework for the adaptive optimization of artificial neural networks wherein the neural network architecture, activation…