Artificial Neural Networks and Machine Learning – ICANN 2023

TRAMA

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.  

SOMMARIO

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.

ALTRE INFORMAZIONI

• Condizione: Nuovo
• ISBN: 9783031441943
• Collana: Lecture Notes in Computer Science
• Dimensioni: 235 x 155 mm
• Formato: Brossura
• Illustration Notes: XXXIV, 529 p. 187 illus., 172 illus. in color.
• Pagine Arabe: 529
• Pagine Romane: xxxiv