Related papers: A Critical View of Vision-Based Long-Term Dynamics…
Accurately modeling open quantum system dynamics is crucial for advancing quantum technologies, yet traditional methods struggle to balance accuracy and efficiency. Machine learning (ML) provides a promising alternative, particularly…
Identifying the physical properties of the surrounding environment is essential for robotic locomotion and navigation to deal with non-geometric hazards, such as slippery and deformable terrains. It would be of great benefit for robots to…
Context awareness is an essential part of mobile and ubiquitous computing. Its goal is to unveil situational information about mobile users like locations and activities. The sensed context can enable many services like navigation, AR, and…
Object rearrangement has recently emerged as a key competency in robot manipulation, with practical solutions generally involving object detection, recognition, grasping and high-level planning. Goal-images describing a desired scene…
Trajectory forecasting, or trajectory prediction, of multiple interacting agents in dynamic scenes, is an important problem for many applications, such as robotic systems and autonomous driving. The problem is a great challenge because of…
Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…
Gait recognition is instrumental in crime prevention and social security, for it can be conducted at a long distance to figure out the identity of persons. However, existing datasets and methods cannot satisfactorily deal with the most…
In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agent itself. Visual reaction entails predicting the future…
Vision-and-language navigation (VLN) aims to enable embodied agents to navigate in realistic environments using natural language instructions. Given the scarcity of domain-specific training data and the high diversity of image and language…
Managing natural resources and mitigating risks from floods, droughts, wildfires, and landslides require models that can accurately predict climate-driven land-surface responses. Traditional models often struggle with spatial generalization…
We consider the commonly encountered situation (e.g., in weather forecasting) where the goal is to predict the time evolution of a large, spatiotemporally chaotic dynamical system when we have access to both time series data of previous…
Autonomous driving gained huge traction in recent years, due to its potential to change the way we commute. Much effort has been put into trying to estimate the state of a vehicle. Meanwhile, learning to forecast the state of a vehicle…
As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a…
This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training,…
Domain gaps between training data (source) and real-world environments (target) often degrade the performance of object detection models. Most existing methods aim to bridge this gap by aligning features across source and target domains but…
Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. Most approaches only exploit the temporal dimension to address the association problem, while relying on…
In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended…
We consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images or EEG). This is…
Vision-based prediction algorithms have a wide range of applications including autonomous driving, surveillance, human-robot interaction, weather prediction. The objective of this paper is to provide an overview of the field in the past…
High quality object proposals are crucial in visual tracking algorithms that utilize region proposal network (RPN). Refinement of these proposals, typically by box regression and classification in parallel, has been popularly adopted to…