相关论文: Active Observer Visual Problem-Solving Methods are…

Trajectory Prediction of dynamic objects is a widely studied topic in the field of artificial intelligence. Thanks to a large number of applications like predicting abnormal events, navigation system for the blind, etc. there have been many…

Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions. Analyzing attention maps offers us a perspective to find out limitations of current VQA…

In machine learning, the term active learning regroups techniques that aim at selecting the most useful data to label from a large pool of unlabelled examples. While supervised deep learning techniques have shown to be increasingly…

This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM'. Our approach leverages the strengths of both classical and learning-based methods, by using analytical path…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

This paper addresses the problem of both actively searching and tracking multiple unknown dynamic objects in a known environment with multiple cooperative autonomous agents with partial observability. The tracking of a target ends when the…

Large language models (LLMs) offer significant promise as a knowledge source for task learning. Prompt engineering has been shown to be effective for eliciting knowledge from an LLM, but alone it is insufficient for acquiring relevant,…

Motion planning methods like navigation functions and harmonic potential fields provide (almost) global convergence and are suitable for obstacle avoidance in dynamically changing environments due to their reactive nature. A common…

Deep active learning aims to reduce the annotation cost for the training of deep models, which is notoriously data-hungry. Until recently, deep active learning methods were ineffectual in the low-budget regime, where only a small number of…

High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed…

In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by…

We consider the optimization of an uncertain objective over continuous and multi-dimensional decision spaces in problems in which we are only provided with observational data. We propose a novel algorithmic framework that is tractable,…

Two prominent strategies that the human visual system uses to reduce incoming information are spatial integration and selective attention. Although spatial integration summarizes and combines information over the visual field, selective…

The present work proposes a Deep Learning architecture for the prediction of various consumer choice behaviors from time series of raw gaze or eye fixations on images of the decision environment, for which currently no foundational models…

This paper frames a general prediction system as an observer traveling around a continuous space, measuring values at some locations, and predicting them at others. The observer is completely agnostic about any particular task being solved;…

Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on…

Model scaling has demonstrated remarkable success through large-scale training on diverse datasets. It remains an open question whether the same paradigm would apply to autonomous driving perception systems due to unique challenges, such as…

We have developed a method for fast and accurate stellar population parameters determination in order to apply it to high resolution galaxy spectra. The method is based on an optimization technique that combines active learning with an…

Understanding how people allocate visual attention is central to Human-Computer Interaction (HCI), yet existing computational models of attention are often either descriptive, task-specific, or difficult to interpret. My dissertation…

Distributed radar sensors enable robust human activity recognition. However, scaling the number of coordinated nodes introduces challenges in feature extraction from large datasets, and transparent data fusion. We propose an end-to-end…