Related papers: Zero-Shot Anticipation for Instructional Activitie…

Anticipating future actions is inherently uncertain. Given an observed video segment containing ongoing actions, multiple subsequent actions can plausibly follow. This uncertainty becomes even larger when predicting far into the future.…

Zero-shot learning in Language & Vision is the task of correctly labelling (or naming) objects of novel categories. Another strand of work in L&V aims at pragmatically informative rather than ``correct'' object descriptions, e.g. in…

In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning…

Inertial parameter identification of industrial robots is an established process, but standard methods using Least Squares or Machine Learning do not consider prior information about the robot and require extensive measurements. Inspired by…

In this paper, we introduce zero-shot cost models which enable learned cost estimation that generalizes to unseen databases. In contrast to state-of-the-art workload-driven approaches which require to execute a large set of training queries…

The purpose of generative Zero-shot learning (ZSL) is to learning from seen classes, transfer the learned knowledge, and create samples of unseen classes from the description of these unseen categories. To achieve better ZSL accuracies,…

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…

Large scale vision and language models can achieve impressive zero-shot recognition performance by mapping class specific text queries to image content. Two distinct challenges that remain however, are high sensitivity to the choice of…

In this paper, we study the problem of enabling a vision-based robotic manipulation system to generalize to novel tasks, a long-standing challenge in robot learning. We approach the challenge from an imitation learning perspective, aiming…

Zero-shot learning (ZSL) can be defined by correctly solving a task where no training data is available, based on previous acquired knowledge from different, but related tasks. So far, this area has mostly drawn the attention from computer…

One of important areas of machine learning research is zero-shot learning. It is applied when properly labeled training data set is not available. A number of zero-shot algorithms have been proposed and experimented with. However, none of…

The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning,…

Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages…

Inspired by human neurological structures for action anticipation, we present an action anticipation model that enables the prediction of plausible future actions by forecasting both the visual and temporal future. In contrast to current…

We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data which features are predictable. Based on the observation that…

The action anticipation task refers to predicting what action will happen based on observed videos, which requires the model to have a strong ability to summarize the present and then reason about the future. Experience and common sense…

We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species…

Tactile sensing plays an irreplaceable role in robotic material recognition. It enables robots to distinguish material properties such as their local geometry and textures, especially for materials like textiles. However, most tactile…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Navigating unfamiliar environments presents significant challenges for household robots, requiring the ability to recognize and reason about novel decoration and layout. Existing reinforcement learning methods cannot be directly transferred…