Related papers: A Compacted Structure for Cross-domain learning on…
Multi-task learning (MTL) aims to enhance the performance and efficiency of machine learning models by simultaneously training them on multiple tasks. However, MTL research faces two challenges: 1) effectively modeling the relationships…
Centralized trajectory optimization in the joint space of multiple robots allows access to a larger feasible space that can result in smoother trajectories, especially while planning in tight spaces. Unfortunately, it is often…
Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial…
Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, relying on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of…
Computation offloading has become a popular solution to support computationally intensive and latency-sensitive applications by transferring computing tasks to mobile edge servers (MESs) for execution, which is known as mobile/multi-access…
In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To handle the challenges posed by subtle and infrequent mistakes, we propose a Dual-Stage Reweighted…
Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have…
Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured…
This paper presents a Long Short-Term Memory network-based Fluid Experiment Data-Driven model (FED-LSTM) for predicting unsteady, nonlinear hydrodynamic forces on the underwater quadruped robot we constructed. Trained on experimental data…
Monocular depth estimation has been increasingly adopted in robotics and autonomous driving for its ability to infer scene geometry from a single camera. In self-supervised monocular depth estimation frameworks, the network jointly…
Detecting manipulated images and videos is an important topic in digital media forensics. Most detection methods use binary classification to determine the probability of a query being manipulated. Another important topic is locating…
Learning a generalizable bimanual manipulation policy is extremely challenging for embodied agents due to the large action space and the need for coordinated arm movements. Existing approaches rely on Vision-Language-Action (VLA) models to…
Monocular depth estimation (MDE) has widely applicable but remains highly challenging due to the inherently ill-posed nature of reconstructing 3D scenes from single 2D images. Modern Vision Foundation Models (VFMs), pre-trained on…
Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this…
Evolutionary multitasking (EMT) is an emerging approach for solving multitask optimization problems (MTOPs) and has garnered considerable research interest. The implicit EMT is a significant research branch that utilizes evolution operators…
We propose DFPNet -- an unsupervised, joint learning system for monocular Depth, Optical Flow and egomotion (Camera Pose) estimation from monocular image sequences. Due to the nature of 3D scene geometry these three components are coupled.…
Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…
Accurate monocular 3D object detection (M3OD) is pivotal for safety-critical applications like autonomous driving, yet its reliability deteriorates significantly under real-world domain shifts caused by environmental or sensor variations.…
Text-to-text transformers have shown remarkable success in the task of multi-task transfer learning, especially in natural language processing (NLP). However, while there have been several attempts to train transformers on different…
Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception. We use a joint self-supervised method to estimate the three geometric elements. Depth network,…