Subudhi / Rout / Sengar Computer Vision, Pattern Recognition, Image Processing, and Graphics

10th National Conference, NCVPRIPG 2025, Jammu, India, July 16–18, 2025, Revised Selected Papers, Part II
Erscheinungsjahr 2026
ISBN: 978-3-032-08511-5
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 482 Seiten

Reihe: Communications in Computer and Information Science

This two-set volume CCIS 2684 and CCIS 2685 constitutes the refereed proceedings of the 10th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2025 held in Jammu, India, during July 16–18, 2025.

The 70 full papers presented in these volumes were carefully reviewed and selected from 266 submissions. The papers cover topics in Active and Real Time Vision, Industrial Vision Systems, Motion and Video Analysis, Hardware for Graphics, Image and Video Compression, Hardware for Vision and IP, Image and Video Retrieval, Visual Special Effects, Object Detection and Recognition, Speech and Audio Processing, Segmentation and Grouping, Document Understanding, Digital Heritage, Medical Image Analysis, Aerial and Satellite Image Analysis, Pattern Recognition, Sensors and Imaging models, Deep Learning.

Zielgruppe

Research

Autoren/Hrsg.

Subudhi, Badri Narayan

Rout, Ranjeet Kumar

Sengar, Brajendra Singh

Inhaltsverzeichnis

.- A Lightweight System for Attention-based Night-time Traffic Accident Detection.

.- Blind Spot Aware and Speed-Sensitive Emergency Vehicle Detection Using YOLO and Faster R-CNN Synergy.

.- Explainable Parallel CNN Model with Dense-Squeeze and Excitation Blocks for Corn Leaf Disease Classification.

.- Attention-Based Multi-patch Hierarchical Network with Non-local Information for Smartphone Image Denoising.

.- Extractive Text Summarization using BERT with Weighted Pooling.

.- Weighted TimeSformer Multi-Region CNN Network for Personalized and Context-aware Activity Localization in Ambient Assisted Living.

.- Prediction of Direction-of-Arrival and Distance for Binaural Sound Sources Using a CRNN-Based Model.

.- Automated Georeferencing of Topographic Maps via OCR and In-Context Multimodal LLM Reasoning.

.- PinTags: A Visual Fiducial Marker System for Logistics.

.- Deep Learning Approach based Object Detection in Underwater SONAR Images.

.- PRISM: Progressive Regional Integration with Synergetic Multi-Attention Transformer for Single Image Super-Resolution.

.- UnTherISR: Unsupervised Approach for Thermal Image Super-Resolution.

.- MAMBA-TBPS: An Efficient Attribute-Relation-Sensitive Framework for Text-Based Person Search.

.- Boosting MobileNet Performance on Embedded Systems Using SE Modules.

.- ContextualVQA: An Efficient Ambient Assisted Monitoring framework Using Visual Question Answering.

.- A Human Vision Neuroscience-Driven Deep Neural Framework for Change Detection in Underwater Scenes.

.- Class-Agnostic Triple Attention Model Towards Optimization and Variable Rate Compression in Wildlife Camera Trap Images.

.- Device-generalized representations for acoustic scene classification.

.- Fake News Detection Using Cellular Automata And Deep Learning.

.- Demystifying Transformer: A Case Study on Graph-Based Interpretability and Attention Layer Dynamics.

.- A Quality-Guided Framework for Low-Light Underwater Image Enhancement Using Degradation Classification and Benchmark Evaluation.

.- Dual-modal Fusion Deep Learning Network for Traffic Targets Detection of Autonomous Vehicles.

.- Hybrid Deep Learning and Explainable AI Approach Towards Trustworthy EV Stock Predictions.

.- WaterIDViT: Open Water Body Extraction in High-resolution Remote Sensing Images Using Vision Transformers.

.- Vision-Based Underwater Docking Station Detection for Autonomous Underwater Vehicles.

.- Real-Time Combat Training Analytics: Skeleton-based Temporal Action Localization in Unstructured Video.

.- High-Precision Traffic Accident Detection Using YOLOv11 Model and Image Processing with Deep Learning Techniques.

.- Late-Fusion-Based Hybrid Deep Learning Architectures for Malware Detection.

.- AUSREGSE: Advanced Underwater Segmentation with ResNet50 with enhancement-guided Squeeze and Excitation Blocks.

.- Improvisation of Yolov4 Algorithm for Multiple Object Tracking Using Kalman Filtering Hungarian Method.

.- Saliency Guided Tile-Based Image Segmentation.

.- Deep Image Prior-Based Segmentation: A Study and proposal of Deeper U-Net.

.- Quantum Convolutional Neural Networks with Residual Learning: Advancing Quantum Model Architectures.

.- Enhancing LSTM-based Piano Music Generation with Self-Attention on the Lakh MIDI Dataset.