Related papers: M2R2: MultiModal Robotic Representation for Tempor…

T2 mapping in fetal brain MRI has the potential to improve characterization of the developing brain, especially at mid-field (0.55T), where T2 decay is slower. However, this is challenging as fetal MRI acquisition relies on multiple…

Accurate transfer of information across multiple sectors to enhance model estimation is both significant and challenging in multi-sector portfolio optimization involving a large number of assets in different classes. Within the framework of…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

Traditional deep learning methods in medical imaging often focus solely on segmentation or classification, limiting their ability to leverage shared information. Multi-task learning (MTL) addresses this by combining both tasks through…

Robot awareness of human actions is an essential research problem in robotics with many important real-world applications, including human-robot collaboration and teaming. Over the past few years, depth sensors have become a standard device…

Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has…

This report presents our method for Temporal Action Localisation (TAL), which focuses on identifying and classifying actions within specific time intervals throughout a video sequence. We employ a data augmentation technique by expanding…

Robots frequently need to perceive object attributes, such as "red," "heavy," and "empty," using multimodal exploratory actions, such as "look," "lift," and "shake." Robot attribute learning algorithms aim to learn an observation model for…

Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and…

Contact-rich manipulation tasks are commonly found in modern manufacturing settings. However, manually designing a robot controller is considered hard for traditional control methods as the controller requires an effective combination of…

Tactile perception is crucial for embodied intelligent robots to recognize objects. Vision-based tactile sensors extract object physical attributes multidimensionally using high spatial resolution; however, this process generates abundant…

Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action…

Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on…

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the…

Recognition of surgical gesture is crucial for surgical skill assessment and efficient surgery training. Prior works on this task are based on either variant graphical models such as HMMs and CRFs, or deep learning models such as Recurrent…

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS…

We introduce a novel framework called RefineVIS for Video Instance Segmentation (VIS) that achieves good object association between frames and accurate segmentation masks by iteratively refining the representations using sequence context.…

Quadrupedal robots hold promising potential for applications in navigating cluttered environments with resilience akin to their animal counterparts. However, their floating base configuration makes them vulnerable to real-world…

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and…