AI 2024: Advances in Artificial Intelligence

This two-volume set LNAI 15442-15443 constitutes the refereed proceedings of the 37th Australasian Joint Conference on Artificial Intelligence, AI 2024, held in Melbourne, VIC, Australia, during November 25-29, 2024.
The 59 full papers presented together with 3 short papers were carefully reviewed and selected from 108 submissions.

Part 1: Knowledge Representation and NLP; Trustworthy and Explainable AI; Machine Learning and Data Mining.
Part 2: Reinforcement Learning and Robotics; Learning Algorithms; Computer Vision; AI for Healthcare.

Contenu

.- Reinforcement Learning and Robotics.
.- ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents.
.- Causally driven hierarchies for Feudal Multi-Agent Reinforcement Learning.
.- Graceful Task Adaptation with a Bi-Hemispheric RL Agent.
.- Towards Virtual Character Control via Partial Story Sifting.
.- Boosting Reinforcement Learning Algorithms in Continuous Robotic Reaching Tasks using Adaptive Potential Functions.
.- Online Deep Reinforcement Learning of Servo Control for a Small-Scale Bio-Inspired Wing.
.- Posterior Tracking Algorithm for Multi-objective Classification Bandits.
.- Learning Algorithms
.- Approximate Nearest Neighbour Search on Dynamic Datasets: An Investigation.
.- Pathwise Gradient Variance Reduction with Control Variates in Variational Inference.
.- Active Continual Learning: On Balancing Knowledge Retention and Learnability.
.- Bayesian Parametric Proportional Hazards Regression with the Fused Lasso.
.- Revisiting Bagging for Stochastic Algorithms.
.- Sampling of Large Probabilistic Graphical Models Using Arithmetic Circuits.
.- Importance-based Pruning for Genetic Programming based Symbolic Regression.
.- Quantifying Manifolds: Do the Manifolds Learned by Generative Adversarial Networks Converge to the Real Data Manifold?.
.- Equality Generating Dependencies in Description Logics via Path Agreements.
.- Computer Vision
.- End-to-end Truck Speed Detection using Deep Multi-Task Learning.
.- Real-Time Lightweight 3D Hand-Object Pose Estimation Using Temporal Graph Convolution Networks.
.- New Perspectives for the Deep Learning Based Photography Aesthetics Assessment.
.- 3DSSG-Cap: A Caption Enhanced Dataset for 3D Visual Grounding.
.- Multi-scale Cooperative Multimodal Transformers for Multimodal Sentiment Analysis in Videos.
.- Chain of Thought Prompting in Vision-Language Model for Vision Reasoning Tasks.
.- Enabling Visual Intelligence by Leveraging Visual Object States in a Neurosymbolic Framework.
.- AI for Healthcare
.- A Self-Adaptive Framework for Efficient Cell Detection and Segmentation in Histopathological
Images with Minimal Expert Input.
.- Learning Low-Energy Consumption Obstacle Detection Models for the Blind.
.- Claimsformer: Pretrained Transformer for Administrative Claims Data to Predict Chronic Conditions.
.- Online Machine Learning for Real-Time Cell Culture Process Monitoring.
.- Motif-induced Subgraph Generative Learning for Explainable Neurological Disorder Detection.
.- Multimodal Hyperbolic Graph Learning for Alzheimer's Disease Detection.
.- Real-Time Human Activity Recognition Using Non-Intrusive Sensing and Continual Learning.
.- Unsupervised dMRI Artifact Detection via Angular Resolution Enhancement and Cycle Consistency Learning.
.- Assessment of Left Atrium Motion Deformation Through Full Cardiac Cycle.
.- Vision-Based Abnormal Action Dataset for Recognising Body Motion Disorders.