LEADER 12382nam 22007455 450 001 9910768469403321 005 20231126161929.0 010 $a981-9983-88-6 024 7 $a10.1007/978-981-99-8388-9 035 $a(MiAaPQ)EBC30974068 035 $a(Au-PeEL)EBL30974068 035 $a(DE-He213)978-981-99-8388-9 035 $a(EXLCZ)9929084009900041 100 $a20231126d2024 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aAI 2023: Advances in Artificial Intelligence$b[electronic resource] $e36th Australasian Joint Conference on Artificial Intelligence, AI 2023, Brisbane, QLD, Australia, November 28?December 1, 2023, Proceedings, Part I /$fedited by Tongliang Liu, Geoff Webb, Lin Yue, Dadong Wang 205 $a1st ed. 2024. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2024. 215 $a1 online resource (574 pages) 225 1 $aLecture Notes in Artificial Intelligence,$x2945-9141 ;$v14471 311 08$aPrint version: Liu, Tongliang AI 2023: Advances in Artificial Intelligence Singapore : Springer Singapore Pte. Limited,c2024 327 $aIntro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Computer Vision -- Multi-graph Laplacian Feature Mapping Incorporating Tag Information for Image Annotation -- 1 Introduction -- 2 Related Work -- 3 Propoesd Method -- 3.1 Multi-graph Laplacian Incorporating Tag Information -- 3.2 Tag Graph Laplacian with Visual Content -- 3.3 Loss Function and Objective Function -- 4 Optimization -- 5 Experimental Results -- 5.1 Experiment Settings -- 5.2 Experimental Performance -- 5.3 The Analysis Parameters -- 6 Conclusion -- References -- Short-Term Solar Irradiance Forecasting from Future Sky Images Generation -- 1 Introduction -- 2 Related Works -- 3 Method -- 3.1 Nowcasting Model -- 3.2 Image Prediction Model -- 3.3 The Forecasting Framework -- 4 Experiments and Results -- 4.1 Datasets -- 4.2 Evaluate Metrics, Data Processing and Hyper-parameters -- 4.3 Nowcasting Results -- 4.4 Forecasting Results -- 5 Conclusion -- References -- No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Preliminaries -- 3.2 Token Selection and Idling -- 3.3 Token Cut Loss -- 3.4 Finetuning -- 4 Experiments -- 4.1 Implementation Settings -- 4.2 Results -- 4.3 Analysis of Token Cut Loss -- 4.4 Analysis of Token Idle Strategy -- 5 Conclusion -- References -- Story Sifting Using Object Detection Techniques -- 1 Introduction -- 2 Background and Related Work -- 3 Approach -- 3.1 Recasting Story Sifting as Object Detection -- 3.2 Representing Story Arcs as Images -- 3.3 Choice of YOLOv5 Model -- 4 Model Development -- 5 Evaluating Model Performance -- 5.1 Model Performance -- 6 Evaluating Time Efficiency -- 7 Detection from a Virtual Storyworld Environment -- 8 Discussion -- 9 Conclusion -- References. 327 $aSimMining-3D: Altitude-Aware 3D Object Detection in Complex Mining Environments: A Novel Dataset and ROS-Based Automatic Annotation Pipeline -- 1 Introduction -- 2 Related Study -- 3 New Dataset: SimMining3D -- 3.1 Data Collection at Simulated Environment -- 3.2 Automatic Annotation -- 4 Perception: Baseline Experiment -- 4.1 Experimental Setup -- 4.2 Results and Discussion -- 5 Conclusion -- References -- Oyster Mushroom Growth Stage Identification: An Exploration of Computer Vision Technologies -- 1 Introduction -- 2 Related Works -- 3 The Monitoring System -- 3.1 The Problem -- 3.2 The Label Map -- 4 Empirical Studies -- 4.1 Settings -- 4.2 Performances -- 5 Conclusion and Future Works -- References -- Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Heads -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Framework Overview -- 3.2 Anchor-Free Head-Body Detection -- 3.3 Joint SimOTA -- 3.4 Tracking Framework -- 3.5 Loss Function -- 3.6 Training Details -- 4 Experiments -- 4.1 MOT Challenge -- 4.2 Qualitative Result on MOT20 -- 4.3 Ablation Study on Joint SimOTA -- 4.4 Crowdhuman -- 5 Conclusion -- References -- SAR2EO: A High-Resolution Image Translation Framework with Denoising Enhancement -- 1 Introduction -- 2 Related Work -- 2.1 GAN -- 2.2 Image-to-Image Translation -- 3 Proposed Method -- 3.1 Preliminary: Pix2pixHD -- 3.2 SAR and EO Images -- 3.3 Denoising Enhanced SAR2EO Framework -- 4 Experiments -- 4.1 Dataset -- 4.2 Metrics -- 4.3 Implementation Details -- 4.4 Main Results -- 4.5 Ablation Studies -- 5 Conclusion -- References -- A New Perspective of Weakly Supervised 3D Instance Segmentation via Bounding Boxes -- 1 Introduction -- 2 Related Work -- 2.1 Fully Supervised Method -- 2.2 Weakly Supervised Method -- 3 Methodology -- 3.1 Problem Description -- 3.2 Cluster-Based Candidate Points Filtering. 327 $a3.3 Smallest-Box Heuristic -- 4 Experiment -- 4.1 Implementation Details -- 4.2 Dataset -- 4.3 Evaluation Metrics and Experiment Results -- 4.4 Ablation Study -- 4.5 Robustness -- 5 Conclusion -- References -- Large-Kernel Attention Network with Distance Regression and Topological Self-correction for Airway Segmentation -- 1 Introduction -- 2 Method -- 2.1 Network Architecture -- 2.2 Prediction Head -- 2.3 Implementation Details -- 3 Experimental Results -- 3.1 Metrics -- 3.2 Comparison with Other Methods -- 3.3 Ablation Study -- 4 Conclusion -- References -- Deep Learning -- WeightRelay: Efficient Heterogeneous Federated Learning on Time Series -- 1 Introduction -- 2 Related Work -- 2.1 Deep Learning for Time Series Classification -- 2.2 Federated Learning on Heterogeneous Devices -- 3 Motivation -- 4 Weight Relay -- 4.1 Heterogeneous Models -- 4.2 Weight Alignment -- 5 Analysis of Weight Relay -- 5.1 Consistency Proof for the Alignment -- 5.2 Macro Explanation of the Training Acceleration -- 5.3 Micro Explanation of the Training Acceleration -- 6 Experiment -- 6.1 Benchmarks -- 6.2 Evaluation Criteria -- 6.3 Experiment Setup -- 6.4 Experiment Result -- 7 Conclusion -- References -- Superpixel Attack -- 1 Introduction -- 2 Preliminaries -- 2.1 Problem Definition -- 2.2 Related Work -- 3 Research on Update Areas -- 3.1 Update Areas of Existing Methods -- 3.2 Color Variance of Update Areas -- 3.3 Compactness of Update Areas -- 3.4 Superpixel Calculated by SLIC -- 3.5 Analysis of Color Variance and Compactness -- 4 Superpixel Attack -- 4.1 Update Areas Using Superpixels -- 4.2 Procedure of Versatile Search -- 5 Experiments -- 6 Conclusion -- References -- Cross Domain Pulmonary Nodule Detection Without Source Data -- 1 Introduction -- 2 Method -- 2.1 Feature Extractor Adaptation -- 2.2 Detection Head Adaptation -- 3 Experiments. 327 $a3.1 Benchmark and Evaluation -- 3.2 Implementation Details -- 3.3 Results -- 4 Related Works -- 5 Conclusion -- References -- 3RE-Net: Joint Loss-REcovery and Super-REsolution Neural Network for REal-Time Video -- 1 Introduction -- 2 Related Work -- 3 Model Design -- 4 Experiments -- 5 Conclusion -- References -- Neural Networks in Forecasting Financial Volatility -- 1 Introduction -- 2 Related Work -- 3 Experimental Comparison of Forecasting Models -- 3.1 Posing the Problem as a Shared Task -- 3.2 Methods -- 3.3 Result Evaluation and Analysis -- 4 Discussion -- References -- CLIP-Based Composed Image Retrieval with Comprehensive Fusion and Data Augmentation -- 1 Introduction -- 2 Related Work -- 2.1 Composed Image Retrieval -- 2.2 Vision-Language Pre-training -- 3 Methodology -- 3.1 Problem Formulation -- 3.2 CLIP-CD -- 4 Experiments -- 4.1 Datasets and Metrics -- 4.2 Implementation Details -- 4.3 Performance Comparison -- 4.4 Ablation Study -- 4.5 Case Study -- 5 Conclusions -- References -- LiDAR Inpainting of UAV Based 3D Point Cloud Using Supervised Learning -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 4 Problem Definition -- 5 Methodology -- 5.1 Simulator -- 5.2 Extracting Individual Point Clouds -- 5.3 Point Cloud Inpainting Model -- 5.4 Inpainting Complete Environments -- 6 Experimental Results -- 7 Conclusion and Future Work -- References -- A Sampling Method for Performance Predictor Based on Contrastive Learning -- 1 Introduction -- 2 Background -- 2.1 Contrastive Learning -- 2.2 Graph Data Sampling Methods -- 3 Approach -- 3.1 Architecture Augmentation -- 3.2 Architecture Maximal Agreement -- 4 Experiments -- 4.1 Overall Performance -- 4.2 Performance Evaluation in NAS Datasets -- 4.3 Ablation Study -- 5 Conclusion -- References. 327 $aAdaptMatch: Adaptive Consistency Regularization for Semi-supervised Learning with Top-k Pseudo-labeling and Contrastive Learning -- 1 Introduction -- 2 Related Work -- 2.1 Consistency Regularization -- 2.2 Contrastive Learning -- 3 Our Approach: AdaptMatch -- 3.1 Data Augmentation -- 3.2 Top-k Label Guessing -- 3.3 Contrastive Learning -- 3.4 Summarization of the Framework -- 4 Experiments -- 4.1 Datasets and Experimental Setup -- 4.2 Main Results -- 5 Ablation Study -- 6 Conclusion -- References -- Estimation of Unmasked Face Images Based on Voice and 3DMM -- 1 Introduction -- 2 Related Research -- 2.1 Studies on Mask Removal -- 2.2 Studies on Estimating Facial Shape from Voice -- 2.3 3D Morphable Model (3DMM) -- 3 Proposed Method -- 3.1 Overview of the Proposal Method -- 3.2 Extraction of Voice Embedding -- 3.3 Combining Voice Embedding and Intermediate Features -- 3.4 Training of Multitasking Module -- 4 Experiments and Results -- 4.1 Dataset -- 4.2 Training Details -- 4.3 Qualitative Evaluation -- 4.4 Quantitative Evaluation -- 5 Discussion -- 5.1 On Qualitative Evaluation -- 5.2 On Quantitative Evaluation -- 6 Conclusion and Future Works -- References -- Aging Contrast: A Contrastive Learning Framework for Fish Re-identification Across Seasons and Years -- 1 Introduction -- 2 Related Work -- 2.1 Deep Learning for Fish Recognition -- 2.2 Contrastive Learning -- 3 Dataset -- 4 Proposed Method -- 4.1 Segmentation and Feature Extraction -- 4.2 Aging Contrast Framework -- 5 Experiments -- 6 Conclusion -- References -- Spatial Bottleneck Transformer for Cellular Traffic Prediction in the Urban City -- 1 Introduction -- 2 Related Work -- 3 Problem Formulation -- 4 Methodology -- 4.1 Spatial Bottleneck Transformer -- 4.2 ST-InducedTran Model -- 5 Experiments -- 5.1 Dataset -- 5.2 Baseline -- 5.3 Implementation Details -- 5.4 Evaluation Metrics. 327 $a6 Results and Discussion. 330 $aThis two-volume set LNAI 14471-14472 constitutes the refereed proceedings of the 36th Australasian Joint Conference on Artificial Intelligence, AI 2023, held in Brisbane, QLD, Australia during November 28 ? December 1, 2023. The 23 full papers presented together with 59 short papers were carefully reviewed and selected from 213 submissions. They are organized in the following topics: computer vision; deep learning; machine learning and data mining; optimization; medical AI; knowledge representation and NLP; explainable AI; reinforcement learning; and genetic algorithm. . 410 0$aLecture Notes in Artificial Intelligence,$x2945-9141 ;$v14471 606 $aArtificial intelligence 606 $aComputer networks 606 $aData mining 606 $aApplication software 606 $aComputer vision 606 $aArtificial Intelligence 606 $aComputer Communication Networks 606 $aData Mining and Knowledge Discovery 606 $aComputer and Information Systems Applications 606 $aComputer Vision 615 0$aArtificial intelligence. 615 0$aComputer networks. 615 0$aData mining. 615 0$aApplication software. 615 0$aComputer vision. 615 14$aArtificial Intelligence. 615 24$aComputer Communication Networks. 615 24$aData Mining and Knowledge Discovery. 615 24$aComputer and Information Systems Applications. 615 24$aComputer Vision. 676 $a006.3 700 $aLiu$b Tongliang$01448665 701 $aWebb$b Geoff$01448666 701 $aYue$b Lin$01448667 701 $aWang$b Dadong$01448668 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910768469403321 996 $aAI 2023: Advances in Artificial Intelligence$93644361 997 $aUNINA