Search Results for author:
Found 24 papers, 8 papers with code
iMedImage Technical Report
Based on this dataset, we developed the iMedImage model, which incorporates the following key features: (1) a unified representation method for diverse modality inputs and medical imaging tasks; (2) multi-level (case-level, image-level, patch-level) image recognition capabilities enhanced by Chain of Thought (CoT) embedding and Mixture of Experts (MoE) strategies.
NVR: Vector Runahead on NPUs for Sparse Memory Access
In this paper, we present NPU Vector Runahead (NVR), a prefetching mechanism tailored for NPUs to address cache miss problems in sparse DNN workloads.
Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systems
Predicting future trajectories of nearby objects, especially under occlusion, is a crucial task in autonomous driving and safe robot navigation.
Value of Information and Reward Specification in Active Inference and POMDPs
Expected free energy (EFE) is a central quantity in active inference which has recently gained popularity due to its intuitive decomposition of the expected value of control into a pragmatic and an epistemic component.
Chromosomal Structural Abnormality Diagnosis by Homologous Similarity
Pathogenic chromosome abnormalities are very common among the general population.
Scan-to-BIM for As-built Roads: Automatic Road Digital Twinning from Semantically Labeled Point Cloud Data
Creating geometric digital twins (gDT) for as-built roads still faces many challenges, such as low automation level and accuracy, limited asset types and shapes, and reliance on engineering experience.
Cypher4BIM: Releasing the Power of Graph for Building Knowledge Discovery
This study aims to explore graphic building information query and develop a graph query language tailored for IFC-Graph.
A Rolling Horizon Restoration Framework for Post-disaster Restoration of Electrical Distribution Networks
Severe weather events such as floods, hurricanes, earthquakes, and large wind or ice storms can cause extensive damage to electrical distribution networks, requiring a multi-day restoration effort.
Resolving uncertainty on the fly: Modeling adaptive driving behavior as active inference
Understanding adaptive human driving behavior, in particular how drivers manage uncertainty, is of key importance for developing simulated human driver models that can be used in the evaluation and development of autonomous vehicles.
A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning
Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment.
A Bayesian Approach to Robust Inverse Reinforcement Learning
We consider a Bayesian approach to offline model-based inverse reinforcement learning (IRL).
Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
Ranked #1 on
3D Object Classification
on ModelNet40
An active inference model of car following: Advantages and applications
We assessed the proposed model, the Active Inference Driving Agent (AIDA), through a benchmark analysis against the rule-based Intelligent Driver Model, and two neural network Behavior Cloning models.
A Light-Weight Communication-Efficient Data Sharing Approach in 5G NR V2X
Timeliness of information is critical for Basic Safety Messages (BSMs) in Vehicle-to-Everything (V2X) communication to enable highly reliable autonomous driving.
Dynamic Local Feature Aggregation for Learning on Point Clouds
Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers.
Performance Analysis of Semi-Persistent Scheduling Throughput in 5G NR-V2X: A MAC Perspective
Subsequently, the average throughput as a function of distance in the partially connected vehicular network is analyzed.
Electric vehicle demand estimation and charging station allocation using urban informatics
The results are fed into the capacitated maximal coverage location problem (CMCLP) model to optimize the spatial layout of public charging stations by maximizing their utilization.
Dilated convolutional neural network-based deep reference picture generation for video compression
Motion estimation and motion compensation are indispensable parts of inter prediction in video coding.
Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
There are 2000 reference restored images and 6003 original underwater images in the unpaired training set.
Single Underwater Image Restoration by Contrastive Learning
Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world.
Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments
As objects are often observed locally, the proposed algorithm uses the symmetrical properties of indoor artificial objects to estimate the occluded parts to obtain more accurate quadric parameters.
Coarse-To-Fine Visual Localization Using Semantic Compact Map
Robust visual localization for urban vehicles remains challenging and unsolved.
PIRM2018 Challenge on Spectral Image Super-Resolution: Dataset and Study
This paper introduces a newly collected and novel dataset (StereoMSI) for example-based single and colour-guided spectral image super-resolution.
Zewen at SemEval-2018 Task 1: An Ensemble Model for Affect Prediction in Tweets
This paper presents a method for Affect in Tweets, which is the task to automatically determine the intensity of emotions and intensity of sentiment of tweets.
