相关论文: AdaGlimpse: Active Visual Exploration with Arbitra…

Enabling robots to explore and act in unfamiliar environments under ambiguous human instructions by interactively identifying task-relevant objects (e.g., identifying cups or beverages for "I'm thirsty") remains challenging for existing…

In this paper we focus on the problem of learning an optimal policy for Active Visual Search (AVS) of objects in known indoor environments with an online setup. Our POMP method uses as input the current pose of an agent (e.g. a robot) and a…

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…

Anticipating actions before they occur is a core challenge in action understanding research. While conventional methods rely on extracting and aggregating temporal information from videos, as humans we can often predict upcoming actions by…

Accurate localization is fundamental for autonomous underwater vehicles (AUVs) to carry out precise tasks, such as manipulation and construction. Vision-based solutions using fiducial marker are promising, but extremely challenging…

Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and scale, while observations impact the quality of sensing decisions. This loopy information…

Visual action planning particularly excels in applications where the state of the system cannot be computed explicitly, such as manipulation of deformable objects, as it enables planning directly from raw images. Even though the field has…

Active perception and foveal vision are the foundations of the human visual system. While foveal vision reduces the amount of information to process during a gaze fixation, active perception will change the gaze direction to the most…

We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network augmented with a global memory that provides context information…

In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper…

Designing agents, capable of learning autonomously a wide range of skills is critical in order to increase the scope of reinforcement learning. It will both increase the diversity of learned skills and reduce the burden of manually…

Micro-gestures are subtle and transient movements triggered by unconscious neural and emotional activities, holding great potential for human-computer interaction and clinical monitoring. However, their low amplitude, short duration, and…

Collision detection via visual fences can significantly enhance the safety of collaborative robotic arms. Existing work typically performs such detection based on pre-deployed stationary cameras outside the robotic arm's workspace. These…

Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability…

This article presents a novel telepresence system for advancing aerial manipulation in dynamic and unstructured environments. The proposed system not only features a haptic device, but also a virtual reality (VR) interface that provides…

Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methods fail to produce accurate and natural motion sequences due to a lack of…

Visual exploration is a task that seeks to visit all the navigable areas of an environment as quickly as possible. The existing methods employ deep reinforcement learning (RL) as the standard tool for the task. However, they tend to be…

We propose a solution for Active Visual Search of objects in an environment, whose 2D floor map is the only known information. Our solution has three key features that make it more plausible and robust to detector failures compared to…

Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a…

Autoexposure (AE) is a critical step applied by camera systems to ensure properly exposed images. While current AE algorithms are effective in well-lit environments with constant illumination, these algorithms still struggle in environments…