19 accepted papers
In domains such as healthcare and marketing, learning optimal individualized dosing policies to maximize utility is crucial, yet high experimental costs impose strict budget constraints, necessitating efficient active policy learning. Existing active learning methods in causal inference primarily fo…
Monocular UAV videos pose a fundamental challenge for 3D reconstruction: dynamic scene modeling requires accurate camera poses, yet recovering poses from long UAV trajectories often fails in texture-sparse regions and in the presence of moving objects. Existing approaches typically handle either pos
Owing to the weak stereo geometry of satellite images, Planar Block Adjustment (PBA) is a predominant technique for correcting geometric distortions in satellite images, which treats elevation as a known constraint and primarily optimizes planar coordinates. Existing PBA methods mainly rely on expli
Accurate estimation of time-varying treatment effects is crucial for optimizing interventions in personalized medicine. However, observational data often contains complex confounding bias and temporal complexities, making counterfactual estimation challenging. We propose Counterfactual Estimation vi
Latent Diffusion Models (LDMs) have recently shown great potential for image restoration owing to their powerful generative priors. However, directly applying them to ultra-high-definition image restoration (UHD-IR) often results in severe global inconsistencies and loss of fine-grained details, pri…
As real-world knowledge continues to evolve, the parametric knowledge acquired by multimodal models during pretraining becomes increasingly difficult to remain consistent with real-world knowledge. Existing research on multimodal knowledge updating focuses only on learning previously unknown knowled…
Three-dimensional scene reconstruction from sparse-view satellite images is a long-standing and challenging task. While 3D Gaussian Splatting (3DGS) and its variants have recently attracted attention for its high efficiency, existing methods remain unsuitable for satellite images due to incompatibil
Semi-dense feature matching methods have shown strong performance in challenging scenarios. However, the existing pipeline relies on a global search across the entire feature map to establish coarse matches, limiting further improvements in accuracy and efficiency. Motivated by this limitation, we p…
Visual SLAM is particularly challenging in environments affected by noise, varying lighting conditions, and darkness. Learning-based optical flow algorithms can leverage multiple modalities to address these challenges, but traditional optical flow-based visual SLAM approaches often require significa
This letter presents an investigation into the estimation of optical and scene flow using RGBD information in scenarios where the RGB modality is affected by noise or captured in dark environments. Existing methods typically rely solely on RGB images or fuse the modalities at later stages, which can
There has been significant interest in searching for off-policy Temporal-Difference (TD) algorithms that find the same solution that would have been obtained in the on-policy regime. An important property of such algorithms is that their expected update has the same fixed point as that of On-policy…
This study proposes a real-time control force (RCF) algorithm for precise force control of hydraulic manipulator arms (HMAs) without the need for force or pressure feedback. The algorithm utilizes the nonlinear relationship between the hydraulic manipulator arm's servo valve pressure, voltage, and d
Three-dimensional (3D) line segments are helpful for scene reconstruction. Most of the existing 3D-line-segment-reconstruction algorithms deal with two views or dozens of small-size images; while in practice there are usually hundreds or thousands of large-size images. In this paper, we propose an e…
We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds). L3Ds are emerging compact representations of patches extracted from point clouds that are learnt from data using a deep learning algorithm. We p
In recent years, a growing number of deep model-based reinforcement learning (RL) methods have been introduced. The interest in deep model-based RL is not surprising, given its many potential benefits, such as higher sample efficiency and the potential for fast adaption to changes in the environment…
We extend the options framework for temporal abstraction in reinforcement learning from discounted Markov decision processes (MDPs) to average-reward MDPs. Our contributions include general convergent off-policy inter-option learning algorithms, intra-option algorithms for learning values and models…
We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and, along with off-policy learning and FA, results in the deadly tri…
We introduce learning and planning algorithms for average-reward MDPs, including 1) the first general proven-convergent off-policy model-free control algorithm without reference states, 2) the first proven-convergent off-policy model-free prediction algorithm, and 3) the first off-policy learning al…
In this paper, we investigate feedback in EWF codes. The considered type of feedback is an acknowledgment, which is a single bit per source block to inform the most important bits have been decoded completely. Moreover, we propose a practical prediction model to calculate the average overheads of su…