Related papers: On Extending Semantic Abstraction for Efficient Se…
Humans excel at learning abstract patterns across different sequences, filtering out irrelevant details, and transferring these generalized concepts to new sequences. In contrast, many sequence learning models lack the ability to abstract,…
Searching for objects in indoor organized environments such as homes or offices is part of our everyday activities. When looking for a target object, we jointly reason about the rooms and containers the object is likely to be in; the same…
Neural implicit representation has attracted attention in 3D reconstruction through various success cases. For further applications such as scene understanding or editing, several works have shown progress towards object compositional…
What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to…
Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to…
We study analogical trajectory transfer, where the goal is to translate motion trajectories in one 3D environment to a semantically analogous location in another. Such a capacity would enable machines to perform analogical spatial…
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for…
Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…
This paper addresses the problem of enabling a robot to search for a semantic object, i.e., an object with a semantic label, in an unknown and GPS-denied environment. For the robot in the unknown environment to detect and find the target…
Dimension reduction (DR) can transform high-dimensional text embeddings into a 2D visual projection facilitating the exploration of document similarities. However, the projection often lacks connection to the text semantics, due to the…
In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…
The existence of variable factors within the environment can cause a decline in camera localization accuracy, as it violates the fundamental assumption of a static environment in Simultaneous Localization and Mapping (SLAM) algorithms.…
Explorative flow visualization allows domain experts to analyze complex flow structures by interactively investigating flow patterns. However, traditional visual interfaces often rely on specialized graphical representations and…
Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…
The definition of symbolic descriptions that consistently represent relevant geometrical aspects in manipulation tasks is a challenging problem that has received little attention in the robotic community. This definition is usually done…
Categorization is a core component of human linguistic competence. We investigate how a transformer-based language model (LM) learns linguistic categories by comparing its behaviour over the course of training to behaviours which…
We propose a structured approach to the problem of retrieval of images by content and present a description logic that has been devised for the semantic indexing and retrieval of images containing complex objects. As other approaches do, we…
Machine-learning algorithms offer immense possibilities in the development of several cognitive applications. In fact, large scale machine-learning classifiers now represent the state-of-the-art in a wide range of object…
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…