相关论文: Integrating Motion into Vision Models for Better V…

This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision,…

There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal…

Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…

Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

Both a good understanding of geometrical concepts and a broad familiarity with objects lead to our excellent perception of moving objects. The human ability to detect and segment moving objects works in the presence of multiple objects,…

Recently neural scene representations have provided very impressive results for representing 3D scenes visually, however, their study and progress have mainly been limited to visualization of virtual models in computer graphics or scene…

This paper presents a novel incremental learning algorithm for pedestrian motion prediction, with the ability to improve the learned model over time when data is incrementally available. In this setup, trajectories are modeled as simple…

An accurate model of the environment and the dynamic agents acting in it offers great potential for improving motion planning. We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

One of the key benefits of model predictive control is the capability of controlling a system proactively in the sense of taking the future system evolution into account. However, often external disturbances or references are not a priori…

Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many…

Many works in collaborative robotics and human-robot interaction focuses on identifying and predicting human behaviour while considering the information about the robot itself as given. This can be the case when sensors and the robot are…

Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for…

Integrating visual features has been proved useful for natural language understanding tasks. Nevertheless, in most existing multimodal language models, the alignment of visual and textual data is expensive. In this paper, we propose a novel…

This paper proposes a pre-trained neural network for handling event camera data. Our model is a self-supervised learning framework, and uses paired event camera data and natural RGB images for training. Our method contains three modules…

In essence, successful grasp boils down to correct responses to multiple contact events between fingertips and objects. In most scenarios, tactile sensing is adequate to distinguish contact events. Due to the nature of high dimensionality…

Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data.…

Many functional elements of human homes and workplaces consist of rigid components which are connected through one or more sliding or rotating linkages. Examples include doors and drawers of cabinets and appliances; laptops; and swivel…

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some…