Related papers: Egocentric RGB+Depth Action Recognition in Industr…
Image segmentation is a vital task for providing human assistance and enhancing autonomy in our daily lives. In particular, RGB-D segmentation-leveraging both visual and depth cues-has attracted increasing attention as it promises richer…
We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space-variant imaging architecture of the mammalian retina with Deep Learning methods. By pre-processing images…
We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for…
Temporal action detection aims to predict the time intervals and the classes of action instances in the video. Despite the promising performance, existing two-stream models exhibit slow inference speed due to their reliance on…
"Looking for things" is a mundane but critical task we repeatedly carry on in our daily life. We introduce a method to develop a human character capable of searching for a randomly located target object in a detailed 3D scene using its…
Egocentric action recognition is essential for healthcare and assistive technology that relies on egocentric cameras because it allows for the automatic and continuous monitoring of activities of daily living (ADLs) without requiring any…
Depth sensors are widely deployed across robotic platforms, and advances in fast, high-fidelity depth simulation have enabled robotic policies trained on depth observations to achieve robust sim-to-real transfer for a wide range of tasks.…
Action recognition is currently one of the top-challenging research fields in computer vision. Convolutional Neural Networks (CNNs) have significantly boosted its performance but rely on fixed-size spatio-temporal windows of analysis,…
This project investigates the human multi-modal behavior identification algorithm utilizing deep neural networks. According to the characteristics of different modal information, different deep neural networks are used to adapt to different…
Robotic grasping, the ability of robots to reliably secure and manipulate objects of varying shapes, sizes and orientations, is a complex task that requires precise perception and control. Deep neural networks have shown remarkable success…
Ensuring robust and real-time obstacle avoidance is critical for the safe operation of autonomous robots in dynamic, real-world environments. This paper proposes a neural network framework for predicting the time and collision position of…
Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by sparsely sampled RGB frames and compressed motion cues (e.g., motion…
The robust recognition and assessment of human actions are crucial in human-robot interaction (HRI) domains. While state-of-the-art models of action perception show remarkable results in large-scale action datasets, they mostly lack the…
Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D…
Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in augmented reality and assisted living. Despite these…
Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high…
Egocentric vision aims to capture and analyse the world from the first-person perspective. We explore the possibilities for egocentric wearable devices to improve and enhance industrial use cases w.r.t. data collection, annotation,…
Achieving precise positioning of the mobile manipulator's base is essential for successful manipulation actions that follow. Most of the RGB-based navigation systems only guarantee coarse, meter-level accuracy, making them less suitable for…
Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile robotic platforms,…
Action recognition is a vital task in computer vision, and many methods are developed to push it to the limit. However, current action recognition models have huge computational costs, which cannot be deployed to real-world tasks on mobile…