Related papers: Touch and Go: Learning from Human-Collected Vision…
When people observe and interact with physical spaces, they are able to associate functionality to regions in the environment. Our goal is to automate dense functional understanding of large spaces by leveraging sparse activity…
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. However, due to unreliable detection, occlusion and fast…
Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The…
The human ability to recognize when an object belongs or does not belong to a particular vision task outperforms all open set recognition algorithms. Human perception as measured by the methods and procedures of visual psychophysics from…
In this paper, we present an approach to tactile pose estimation from the first touch for known objects. First, we create an object-agnostic map from real tactile observations to contact shapes. Next, for a new object with known geometry,…
Understanding how humans use physical contact to interact with the world is key to enabling human-centric artificial intelligence. While inferring 3D contact is crucial for modeling realistic and physically-plausible human-object…
Visuo-tactile sensors aim to emulate human tactile perception, enabling robots to precisely understand and manipulate objects. Over time, numerous meticulously designed visuo-tactile sensors have been integrated into robotic systems, aiding…
In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly…
A dataset is crucial for model learning and evaluation. Choosing the right dataset to use or making a new dataset requires the knowledge of those that are available. In this work, we provide that knowledge, by reviewing twenty datasets that…
Egocentric vision is an emerging field of computer vision that is characterized by the acquisition of images and video from the first person perspective. In this paper we address the challenge of egocentric human action recognition by…
This paper presents a new method to describe spatio-temporal relations between objects and hands, to recognize both interactions and activities within video demonstrations of manual tasks. The approach exploits Scene Graphs to extract key…
Most current works in Sim2Real learning for robotic manipulation tasks leverage camera vision that may be significantly occluded by robot hands during the manipulation. Tactile sensing offers complementary information to vision and can…
Humans represent and discriminate the objects in the same category using their properties, and an intelligent robot should be able to do the same. In this paper, we build a robot system that can autonomously perceive the object properties…
The ability for an autonomous agent or robot to track and identify potentially multiple objects in a dynamic environment is essential for many applications, such as automated surveillance, traffic monitoring, human-robot interaction, etc.…
This paper proposes an idea of building an interface to merge the existing technologies like Image processing, Internet of Things, Sixth sense, etc. at one place to reduce the hardware restrictions imposed on a user and improve the…
When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose. However, most existing object pose tracking systems in robotics rely exclusively on visual signals, which…
Human eye tracking devices can help to investigate principles of processing visual information by humans. The attention focus movement during the gaze can be used for behavioural analysis of humans. In this work we describe our experimental…
Collecting 3D object datasets involves a large amount of manual work and is time consuming. Getting complete models of objects either requires a 3D scanner that covers all the surfaces of an object or one needs to rotate it to completely…
Training deep-learning-based vision systems require the manual annotation of a significant number of images. Such manual annotation is highly time-consuming and labor-intensive. Although previous studies have attempted to eliminate the…
Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects…