Full Description
The 10-volume set LNCS 14254-14263 constitutes the proceedings of the 32nd International Conference on Artificial Neural Networks and Machine Learning, ICANN 2023, which took place in Heraklion, Crete, Greece, during September 26-29, 2023.
The 426 full papers and 9 short papers included in these proceedings were carefully reviewed and selected from 947 submissions. ICANN is a dual-track conference, featuring tracks in brain inspired computing on the one hand, and machine learning on the other, with strong cross-disciplinary interactions and applications.
Contents
A Comparative Study of Sentence Embedding Models for Assessing Semantic Variation.- A Deep Learning based Method for Generating Holographic Acoustic Fields from Phased Transducer Arrays.- A Depth-guided Attention Strategy for Crowd Counting.- A Noise Convolution Network for Tampering Detection.- Attention-based Feature Interaction Deep Factorization Machine for CTR Prediction.- Block-level Stiffness Analysis of Residual Networks.- CKNA: Kernel Hyperparameters Optimization Method for Group-wise CNNs.- Conditional Convolution Residual Network for Efficient Super-Resolution.- Cross Attention with Deep Local Features for Few-shot Image Classification.- Deep Video Compression Based on 3D Convolution Artifacts Removal and Attention Compression Module.- Deep-learning Based Three Channel Defocused Projection Profilometry.- Depthwise Convolution with Channel Mixer: Rethinking MLP in MetaFormer for Faster and More Accurate Vehicle Detection.- DLUIO: Detecting Useful Investor Opinions by Deep Learning.- Dynamic obstacle avoidance for unmanned aerial vehicle using dynamic vision sensor.- Empirical Study on the Effect of Residual Networks on the Expressiveness of Linear Regions.- Energy Complexity Model for Convolutional Neural Networks.- Enhancing the Interpretability of Deep Multi-Agent Reinforcement Learning via Neural Logic Reasoning.- Evidential Robust Deep Learning for Noisy Text2text Question Classification.- FBPFormer: Dynamic Convolutional Transformer for Global-Local-Contexual Facial Beauty Prediction.- Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks.- Interaction of Generalization and Out-of-Distribution Detection Capabilities in Deep Neural Networks.- Long-distance Pipeline Intrusion Warning Based on Environment Embedding From Distributed Optical Fiber Sensing.- LSA3D: Lightweight Separate Asynchronous 3D Convolutional Neural Network for Gait Recognition.- MADNet: EEG-based Depression Detection using a Deep Convolution Neural Network Framework with Multi-dimensional Attention.- Maintenance automation using deep learning methods a case study from the aerospace industry.- MCASleepNet: Multimodal channel attention-based deep neural network for automatic sleep staging.- Multi-label Image Deep Hashing with Hybrid Loss of Global Center and Local Alignment.- Multi-relation Representation Learning based Deep Network for Patent Classification.- One Hip Wonder: 1D-CNNs Reduce Sensor Requirements for Everyday Gait Analysis.- Patches Channel Attention For Human Sitting Posture Recognition.- RA-Net: A Deep Learning Approach based on Residual Structure and Attention Mechanism for Image Copy-move Forgery Detection.- Rethinking CNN Architectures in Transformer Detectors.- Robustness of Biologically-inspired filter-based ConvNet to Signal Perturbation.- Self-Supervised Graph Convolution for Video Moment Retrieval.- Siamese Network based on MLP and Multi-head Cross Attention for Visual Object Tracking.- Taper Residual Dense Network for Audio Super-Resolution.- VPNDroid: Malicious Android VPN detection using a CNN-RF method.- Who breaks early, looses: goal oriented training of deep neural networks based on port Hamiltonian dynamics.- BLR:A multi-modal sentiment analysis model.- Detecting Negative Sentiment on Sarcastic Tweets for Sentiment Analysis.- Local or Global: The Variation in the Encoding of Style Across Sentiment and Formality.- Prompt-oriented Fine-tuning Dual Bert for Aspect-Based Sentiment Analysis.- Towards Energy-Efficient Sentiment Classification with Spiking Neural Networks.- Using Masked Language Modeling to Enhance BERT-based Aspect-Based Sentiment Analysis for Affective Token Prediction.
