A Shallow Information Enhanced Efficient Small Object Detector based on YOLOv5 -- Adaptive Dehazing YOLO for Object Detection -- Adaptive Training Strategies for Small Object Detection using Anchor-based Detectors -- Automatic Driving Scenarios: A Cross-Domain Approach for Object Detection -- Dual Attention Feature Fusion for Visible-Infrared Object Detection -- Feature Sniffer: A Stealthy Inference Attacks Framework on Split Learning -- Few-Shot Object Detection via Transfer Learning and Contrastive Reweighting -- GaitFusion: Exploring the fusion of silhouettes and optical flow for gait recognition -- Gradient Adjusted and Weight Rectified Mean Teacher for Source-free Object Detection -- IMAM: Incorporating multiple attention mechanisms for 3D Object Detection from Point Cloud -- LGF2: Local and Global Feature Fusion for Text-guided Object Detection -- MLF-DET: Multi-Level Fusion for Cross-Modal 3D Object Detection -- Object Detection inFoggy Images with Transmission Map Guidance -- PE-YOLO: Pyramid Enhancement Network for Dark Object Detection -- Region Feature Disentanglement for Domain Adaptive Object Detection -- ROFusion: Efficient Object Detection using Hybrid Point-wise Radar-Optical Fusion -- SDGC-YOLOv5: A more accurate model for small object detection -- The Statistical Characteristics of P3a and P3b Subcomponents in Electroencephalography Signals -- Transforming Limitations into Advantages: Improving Small Object Detection Accuracy with SC-AttentionIoU Loss Function -- Visual-Haptic-Kinesthetic Object Recognition with Multimodal Transformer -- X-shape Feature Expansion Network for Salient Object Detection in Optical Remote Sensing Images -- Aggregate Distillation For Top-K Recommender System -- Candidate-Aware Dynamic Representation for News Recommendation -- Category Enhanced Dual View Contrastive Learning for Session-based Recommendation -- Electronic Medical Record Recommendation System Based on Deep Embedding Learning with Named Entity Recognition -- Incremental Recommendation Algorithm based on the Influence Propagation Model -- Scenic Spot Recommendation Method Integrating Knowledge Graph And Distance Cost -- A Unified Video Semantics Extraction and Noise Object Suppression Network for Video Saliency Detection -- Adaptive Token Excitation With Negative Selection For Video-Text Retrieval -- Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization -- Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition -- Correction while Recognition: Combining Pretrained Language Model for Taiwan-accented Speech Recognition -- Cross-Camera Prototype Learning for Intra-Camera Supervised Person Re-Identification -- ECDet: A Real-time Vehicle Detection Network for CPU-only Devices -- Gated Multi-Modal Fusion with Cross-Modal Contrastive Learning for VideoQuestion Answering -- Learning Video Localization on Segment-Level Video Copy Detection with Transformer -- Linear Transformer-GAN: A Novel Architecture to Symbolic Music Generation -- MBMS-GAN: Multi-Band Multi-Scale Adversarial Learning for Enhancement of Coded Speech at Very Low Rate -- OWS-Seg: online weakly supervised video instance segmentation via contrastive learning -- Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition -- Self-Supervised Video Object Segmentation Using Motion Feature Compensation -- Space-Time Video Super-Resolution Based on Long-Term Time Dependence.

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, 9 short papers and 9 abstract 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. .