Related papers: Depth-Aware Multi-Grid Deep Homography Estimation …

Humans effortlessly identify objects by leveraging a rich understanding of the surrounding scene, including spatial relationships, material properties, and the co-occurrence of other objects. In contrast, most computational object…

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a…

Multi-label classification (MLC) studies the problem where each instance is associated with multiple relevant labels, which leads to the exponential growth of output space. MLC encourages a popular framework named label compression (LC) for…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…

Homography estimation is a fundamental task in computer vision with applications in diverse fields. Recent advances in deep learning have improved homography estimation, particularly with unsupervised learning approaches, offering increased…

In this work we use the persistent homology method, a technique in topological data analysis (TDA), to extract essential topological features from the data space and combine them with deep learning features for classification tasks. In TDA,…

In this paper, we propose a novel, convolutional neural network model to extract highly precise depth maps from missing viewpoints, especially well applicable to generate holographic 3D contents. The depth map is an essential element for…

Image color harmonization algorithm aims to automatically match the color distribution of foreground and background images captured in different conditions. Previous deep learning based models neglect two issues that are critical for…

Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. While a number of methods have been proposed for face attribute estimation, most of them did not explicitly consider the…

Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail…

Planar object tracking plays an important role in AI applications, such as robotics, visual servoing, and visual SLAM. Although the previous planar trackers work well in most scenarios, it is still a challenging task due to the rapid motion…

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While…

Persistent homology, a technique from computational topology, has recently shown strong empirical performance in the context of graph classification. Being able to capture long range graph properties via higher-order topological features,…

Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…

Aerial image registration or matching is a geometric process of aligning two aerial images captured in different environments. Estimating the precise transformation parameters is hindered by various environments such as time, weather, and…

Deep neural networks are playing an important role in state-of-the-art visual recognition. To represent high-level visual concepts, modern networks are equipped with large convolutional layers, which use a large number of filters and…

Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses. However, surrogate objectives of correspondence learning in 3D space are a step away from the true ones of…

Emerging learned holography approaches have enabled faster and high-quality hologram synthesis, setting a new milestone toward practical holographic displays. However, these learned models require training a dedicated model for each set of…

Image stitching aims at stitching the images taken from different viewpoints into an image with a wider field of view. Existing methods warp the target image to the reference image using the estimated warp function, and a homography is one…