Related papers: Scene Image Representation by Foreground, Backgrou…

Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved…

This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…

This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale…

Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection,…

Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

The field of image classification has shown an outstanding success thanks to the development of deep learning techniques. Despite the great performance obtained, most of the work has focused on natural images ignoring other domains like…

We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene…

Automatic image synthesis research has been rapidly growing with deep networks getting more and more expressive. In the last couple of years, we have observed images of digits, indoor scenes, birds, chairs, etc. being automatically…

Persistent topological properties of an image serve as an additional descriptor providing an insight that might not be discovered by traditional neural networks. The existing research in this area focuses primarily on efficiently…

Similarity-preserving hashing is a commonly used method for nearest neighbour search in large-scale image retrieval. For image retrieval, deep-networks-based hashing methods are appealing since they can simultaneously learn effective image…

We present a system for multi-level scene awareness for robotic manipulation. Given a sequence of camera-in-hand RGB images, the system calculates three types of information: 1) a point cloud representation of all the surfaces in the scene,…

Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be…

Over the years, scene understanding has attracted a growing interest in computer vision, providing the semantic and physical scene information necessary for robots to complete some particular tasks autonomously. In 3D scenes, rich spatial…

Comprehensive 3D scene understanding, both geometrically and semantically, is important for real-world applications such as robot perception. Most of the existing work has focused on developing data-driven discriminative models for scene…

Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…

The existing image feature extraction methods are primarily based on the content and structure information of images, and rarely consider the contextual semantic information. Regarding some types of images such as scenes and objects, the…

Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image…

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first…