Related papers: Grid Cell Path Integration For Movement-Based Visu…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant…

Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs. In almost all cases so far, however, they have been applied to directly recovering a final solution from raw inputs, without…

Image classification is an essential task in computer vision, which aims to categorise a set of images into different groups based on some visual criteria. Existing methods, such as convolutional neural networks, have been successfully…

Recent advances in deep learning have led to significant progress in the computer vision field, especially for visual object recognition tasks. The features useful for object classification are learned by feed-forward deep convolutional…

Grid cells in the medial entorhinal cortex (MEC) and place cells in the hippocampus (HC) both form spatial representations. Grid cells fire in triangular grid patterns, while place cells fire at specific locations and respond to contextual…

A common approach for modeling the environment of an autonomous vehicle are dynamic occupancy grid maps, in which the surrounding is divided into cells, each containing the occupancy and velocity state of its location. Despite the advantage…

Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solutions have some defects: they mostly ignore the intra-view…

Stairs are common building structures in urban environments, and stair detection is an important part of environment perception for autonomous mobile robots. Most existing algorithms have difficulty combining the visual information from…

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint…

In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud. Towards this end, we encode the point cloud efficiently in a fixed radius near-neighbors graph. We design a graph neural network, named Point-GNN,…

We propose a neural network-based approach for collision detection with deformable objects. Unlike previous approaches based on bounding volume hierarchies, our neural approach does not require an update of the spatial data structure when…

3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work often uses a tracking-by-detection pipeline, where the feature of each object is extracted independently to compute an affinity matrix. Then, the affinity matrix…

Path integration is a navigation strategy widely observed in nature where an animal maintains a running estimate of its location during an excursion. Evidence suggests it is both ancient and ubiquitous in nature. Over the past century or…

Motion prediction is a challenging task for autonomous vehicles due to uncertainty in the sensor data, the non-deterministic nature of future, and complex behavior of agents. In this paper, we tackle this problem by representing the scene…

Human-robot walking with prosthetic legs and exoskeletons, especially over complex terrains such as stairs, remains a significant challenge. Egocentric vision has the unique potential to detect the walking environment prior to physical…

Despite their success, modern convolutional neural networks (CNNs) exhibit fundamental limitations, including data inefficiency, poor out-of-distribution generalization, and vulnerability to adversarial perturbations. These shortcomings can…

Can the intrinsic relation between an object and the room in which it is usually located help agents in the Visual Navigation Task? We study this question in the context of Object Navigation, a problem in which an agent has to reach an…

Visual perception plays a pivotal role in enabling autonomous behavior, offering a cost-effective and efficient alternative to complex multi-sensor systems. However, robust segmentation remains a challenge in complex scenarios. To address…

Being able to grasp objects is a fundamental component of most robotic manipulation systems. In this paper, we present a new approach to simultaneously reconstruct a mesh and a dense grasp quality map of an object from a depth image. At the…