Related papers: Video-Based Performance Evaluation for ECR Drills …
Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this…
Extended reality (XR) technologies-encompassing virtual reality (VR), augmented reality (AR), and mixed reality (MR) are transforming cognitive assessment and training by offering immersive, interactive environments that simulate real-world…
Cognitive training has shown promising results for delivering improvements in human cognition related to attention, problem solving, reading comprehension and information retrieval. However, two frequently cited problems in cognitive…
In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this…
Recently, synthetic data generation and realistic rendering has advanced tasks like target tracking and human pose estimation. Simulations for most robotics applications are obtained in (semi)static environments, with specific sensors and…
Reinforcement learning (RL) for robot control typically requires a detailed representation of the environment state, including information about task-relevant objects not directly measurable. Keypoint detectors, such as spatial autoencoders…
Concrete workability measure is mostly determined based on subjective assessment of a certified assessor with visual inspections. The potential human error in measuring the workability and the resulting unnecessary adjustments for the…
This paper investigates how rendering engines, like Unreal Engine 4 (UE), can be used to create synthetic images to supplement datasets for deep computer vision (CV) models in image abundant and image limited use cases. Using rendered…
Physical rehabilitation plays a crucial role in restoring functional abilities, but traditional approaches often face challenges in terms of cost, accessibility, and personalized monitoring. Asynchronous physical rehabilitation has gained…
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However, the evaluation of neural IR has so far been limited to…
Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement,…
Videos provide a rich source of information, but it is generally hard to extract dynamical parameters of interest. Inferring those parameters from a video stream would be beneficial for physical reasoning. Robots performing tasks in dynamic…
Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning…
Large vision-language models have achieved remarkable capabilities by training on massive internet-scale data, yet a fundamental asymmetry persists: while LLMs can leverage self-supervised pretraining on abundant text and image data, the…
Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. Most published results on deep RL benchmarks compare point estimates of aggregate performance such as…
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train…
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…
Researchers have been using simulation-based methods for drone-assisted inspection training. Multiple brain regions are associated with information processes and decision-making, and the connectivity of these regions may further influence…
Spatial reasoning in vision language models (VLMs) remains fragile when semantics hinge on subtle temporal or geometric cues. We introduce a synthetic benchmark that probes two complementary skills: situational awareness (recognizing…
The state of the art in video super-resolution (SR) are techniques based on deep learning, but they perform poorly on real-world videos (see Figure 1). The reason is that training image-pairs are commonly created by downscaling a…