Related papers: Learning an Interactive Segmentation System

Most existing approaches to video instance segmentation comprise multiple modules that are heuristically combined to produce the final output. Formulating a purely learning-based method instead, which models both the temporal aspect as well…

Environmental conditions and external effects, such as shocks, have a significant impact on the calibration parameters of visual-inertial sensor systems. Thus long-term operation of these systems cannot fully rely on factory calibration.…

Instance segmentation is a computer vision task where separate objects in an image are detected and segmented. State-of-the-art deep neural network models require large amounts of labeled data in order to perform well in this task. Making…

Often, robots are asked to execute primitive movements, whether as a single action or in a series of actions representing a larger, more complex task. These movements can be learned in many ways, but a common one is from demonstrations…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

Graphical models are useful tools for describing structured high-dimensional probability distributions. Development of efficient algorithms for learning graphical models with least amount of data remains an active research topic.…

Physical agents that can autonomously generate engaging, life-like behaviour will lead to more responsive and interesting robots and other autonomous systems. Although many advances have been made for one-to-one interactions in well…

In this paper we present an alternative approach to symbolic segmentation; instead of implementing a new method we approach symbolic segmentation as an algorithm selection problem. That is, let there be $n$ available algorithms for symbolic…

The proliferation of creative video content has driven demand for adapting language models to handle video input and enable multimodal understanding. However, end-to-end models struggle to process long videos due to their size and…

This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning…

Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement learning-based method for automatically adjusting the…

Due to low tissue contrast, irregular object appearance, and unpredictable location variation, segmenting the objects from different medical imaging modalities (e.g., CT, MR) is considered as an important yet challenging task. In this…

This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same…

This paper presents the design and development of an innovative interactive robotic system to enhance audience engagement using character-like personas. Built upon the foundations of persona-driven dialog agents, this work extends the…

Purpose: In this paper, we investigate a framework for interactive brain tumor segmentation which, at its core, treats the problem of interactive brain tumor segmentation as a machine learning problem. Methods: This method has an advantage…

Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, and bounding boxes. Recently, vision transformers have achieved…

This paper studies Clinical Intelligent Decision Support Systems (CIDSSs) for lung cancer segmentation, which are based on deep neural nets. A new interactive CIDSS is proposed and compared with previous approaches. Addition-ally, the…

Semantic segmentation enables robots to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown environments,…

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…

Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic…