Related papers: FCA-RAC: First Cycle Annotated Repetitive Action C…

This study examines how Critical Care Air Transport Team (CCATT) members are trained using mixed-reality simulations that replicate the high-pressure conditions of aeromedical evacuation. Each team - a physician, nurse, and respiratory…

Current datasets for action recognition tasks face limitations stemming from traditional collection and generation methods, including the constrained range of action classes, absence of multi-viewpoint recordings, limited diversity, poor…

Model predictive control (MPC) is a promising technique for motion cueing in driving simulators, but its high computation time limits widespread real-time application. This paper proposes a hybrid algorithm that combines filter-based and…

The recent introduction of the AVA dataset for action detection has caused a renewed interest to this problem. Several approaches have been recently proposed that improved the performance. However, all of them have ignored the main…

In many settings, we have multiple data sets (also called views) that capture different and overlapping aspects of the same phenomenon. We are often interested in finding patterns that are unique to one or to a subset of the views. For…

Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making…

Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation…

Crowd counting plays a vital role in public safety, traffic regulation, and smart city management. However, despite the impressive progress achieved by CNN- and Transformer-based models, their performance often deteriorates when applied…

Learning transferable latent actions from large-scale object manipulation videos can significantly enhance generalization in downstream robotics tasks, as such representations are agnostic to different robot embodiments. Existing approaches…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Machine learning systems are being used to automate many types of laborious labeling tasks. Facial actioncoding is an example of such a labeling task that requires copious amounts of time and a beyond average level of human domain…

Data generation is a data augmentation technique for enhancing the generalization ability for skeleton-based human action recognition. Most existing data generation methods face challenges to ensure the temporal consistency of the dynamic…

Temporal action segmentation (TAS) demands dense temporal supervision, yet most of the annotation cost in untrimmed videos is spent identifying and refining action transitions, where segmentation errors concentrate and small temporal shifts…

Traditional temporal action detection (TAD) usually handles untrimmed videos with small number of action instances from a single label (e.g., ActivityNet, THUMOS). However, this setting might be unrealistic as different classes of actions…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions. However, their high inference cost-stemming from large-scale token computation and…

Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further…

In this work we employ multitask learning to capitalize on the structure that exists in related supervised tasks to train complex neural networks. It allows training a network for multiple objectives in parallel, in order to improve…

We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we…

Motion Cueing Algorithms (MCAs) encode the movement of simulated vehicles into movement that can be reproduced with a motion simulator to provide a realistic driving experience within the capabilities of the machine. This paper introduces a…

Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects.…