Related papers: Seeing the Unseen: Visual Common Sense for Semanti…
End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of…
Robotic tasks such as planning and navigation require a hierarchical semantic understanding of a scene, which could include multiple floors and rooms. Current methods primarily focus on object segmentation for 3D scene understanding.…
Human visual scene understanding is so remarkable that we are able to recognize a revisited place when entering it from the opposite direction it was first visited, even in the presence of extreme variations in appearance. This capability…
Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling semantic similarity,…
We present a Visual Place Recognition system that follows the two-stage format common to image retrieval pipelines. The system encodes images of places by employing the activations of different layers of a pre-trained, off-the-shelf, VGG16…
Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world.…
To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships…
This paper focuses on vision-based pose estimation for multiple rigid objects placed in clutter, especially in cases involving occlusions and objects resting on each other. Progress has been achieved recently in object recognition given…
Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…
Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents…
Composed image retrieval is a type of image retrieval task where the user provides a reference image as a starting point and specifies a text on how to shift from the starting point to the desired target image. However, most existing…
Color images are easy to understand visually and can acquire a great deal of information, such as color and texture. They are highly and widely used in tasks such as segmentation. On the other hand, in indoor person segmentation, it is…
Object rearrangement is the problem of enabling a robot to identify the correct object placement in a complex environment. Prior work on object rearrangement has explored a diverse set of techniques for following user instructions to…
Visual Place Recognition (VPR) is often characterized as being able to recognize the same place despite significant changes in appearance and viewpoint. VPR is a key component of Spatial Artificial Intelligence, enabling robotic platforms…
When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant information and sequentially combining it to build a representation from the sensory data. In this…
Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense…
Understanding and extracting 3D information of objects from monocular 2D images is a fundamental problem in computer vision. In the task of 3D object pose estimation, recent data driven deep neural network based approaches suffer from…
This work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples. Where existing work relies on transferring global attribute or object information from seen to…
Occlusions of objects is one of the indispensable problems in Computer vision. While Convolutional Neural Net-works (CNNs) provide various state of the art approaches for regular image classification, they however, prove to be not as…
The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene…