Related papers: Learning Deep Structured Multi-Scale Features usin…
TGraphX presents a novel paradigm in deep learning by unifying convolutional neural networks (CNNs) with graph neural networks (GNNs) to enhance visual reasoning tasks. Traditional CNNs excel at extracting rich spatial features from images…
Deep learning methods are powerful tools but often suffer from expensive computation and limited flexibility. An alternative is to combine light-weight models with deep representations. As successful cases exist in several visual problems,…
Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…
Deep Convolutional Neural Networks (CNN) have drawn great attention in image super-resolution (SR). Recently, visual attention mechanism, which exploits both of the feature importance and contextual cues, has been introduced to image SR and…
Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…
Convolutional neural networks (CNNs) have demonstrated superior performance in super-resolution (SR). However, most CNN-based SR methods neglect the different importance among feature channels or fail to take full advantage of the…
Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on…
This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi- scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from…
Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video. Recently, increasing attention has been paid on generalizing CNNs to graph or network data which is…
Distinguishing between computer-generated (CG) and natural photographic (PG) images is of great importance to verify the authenticity and originality of digital images. However, the recent cutting-edge generation methods enable high…
Accurate prediction of molecular properties is essential in drug discovery and related fields. However, existing graph neural networks (GNNs) often struggle to simultaneously capture both local and global molecular structures. In this work,…
Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can significantly enhance…
Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…
Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to…
Learning fine-grained details is a key issue in image aesthetic assessment. Most of the previous methods extract the fine-grained details via random cropping strategy, which may undermine the integrity of semantic information. Extensive…
Fully unsupervised 3D representation learning has gained attention owing to its advantages in data collection. A successful approach involves a viewpoint-aware approach that learns an image distribution based on generative models (e.g.,…
In this paper, we propose an accurate edge detector using richer convolutional features (RCF). Since objects in nature images have various scales and aspect ratios, the automatically learned rich hierarchical representations by CNNs are…
Graph Neural Networks (GNNs) with attention have been successfully applied for learning visual feature matching. However, current methods learn with complete graphs, resulting in a quadratic complexity in the number of features. Motivated…
Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large…
In this work we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRF) with Deep Learning: (a) our structured prediction task has a unique global optimum that is obtained exactly…