Related papers: Semantic Line Detection Using Mirror Attention and…

The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class…

Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging. In this paper, we propose Stereo Mixture Density Networks…

For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting…

Image restoration is a low-level vision task which is to restore degraded images to noise-free images. With the success of deep neural networks, the convolutional neural networks surpass the traditional restoration methods and become the…

Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global…

Attention mechanisms are often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention models are insufficient for the learning…

Semantic code clone detection is the task of detecting whether two snippets of code implement the same functionality (e.g., Sort Array). Recently, many neural models achieved near-perfect performance on this task. These models seek to make…

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer…

Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance…

Semantic communication has recently attracted significant interest from both industry and academia due to its potential to transform the existing data-focused communication architecture towards a more generally intelligent and goal-oriented…

A novel algorithm to detect road lanes in the eigenlane space is proposed in this paper. First, we introduce the notion of eigenlanes, which are data-driven descriptors for structurally diverse lanes, including curved, as well as straight,…

In this work, we present a method for landmark retrieval that utilizes global and local features. A Siamese network is used for global feature extraction and metric learning, which gives an initial ranking of the landmark search. We utilize…

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…

The inability to interpret the model prediction in semantically and visually meaningful ways is a well-known shortcoming of most existing computer-aided diagnosis methods. In this paper, we propose MDNet to establish a direct multimodal…

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance…

Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…

Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly based on insufficient hand-crafted rules that only partially…

Recent state-of-the-art scene text recognition methods have primarily focused on horizontal text in images. However, in several Asian countries, including China, large amounts of text in signs, books, and TV commercials are vertically…

Time series anomaly detection has achieved remarkable progress in recent years. However, evaluation practices have received comparatively less attention, despite their critical importance. Existing metrics exhibit several limitations: (1)…

In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and…