Mehr lesen
Inhaltsverzeichnis
.- Segmentation.
.- CarboFormer: A Lightweight Semantic Segmentation Architecture forEfficient Carbon Dioxide Detection Using Optical Gas Imaging.
.- Towards Facilitating Manual Annotations of 3D Hand Pose by Making Predictions from Partial Annotations.
.- Distribution-Preserving Data Curation for Semantic Segmentation.
.- 3D.
.- Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning.
.- Generating High-Fidelity Eucalyptus Point Clouds: A Comparative Study from GANs to Diffusion Models.
.- Probabilistic Direct Structure from Motion via Hierarchical Reparameterization Trick.
.- Video Analysis and Event Recognition.
.- Seeing Through Words: A Zero-Shot Multimodal Audio DescriptionSystem with Foundation Models.
.- Supervised Contrastive Frame Aggregation for Video Representation Learning.
.- CMAD: Conditional Modeling-Adapter Diffusion for Video Super-Resolution.
.- Biometrics.
.- Dataset Bias in Hand Pose Estimation Benchmarks.
.- FC-IQA: Forehead-Creases Biometric Image Quality Assessment and Evaluation.
.- Quantifying the Impact of Face Obfuscation on the Visual Extraction of Semantic Information.
.- CLRecogEye : Curriculum learning towards exploiting convolution features for Dynamic Iris Recognition.
.- Improving GAN Inversion with Joint Identity and Attribute Constraints.
.- Visualization.
.- SWR-Viz: AI-assisted Interactive Visual Analytics Framework for Ship Weather Routing.
.- Evaluating Prompting Strategies for Chart Question Answering with Large Language Models.
.- Evaluating Line Chart Strategies for Mitigating Density of Temporal Data: The Impact on Trend, Prediction, and Decision-Making.
.- Low-Cost Immersive Molecule Visualization from Hand-Drawn Smartwatch Input for Virtual Reality Learning.
.- Assessment of Foot Clearance Impairments in Glaucoma Patients Using Smart Insoles.
.- Poster.
.- A conditional variational autoencoder to learn mappings between ALS and TLS measured forests.
.- SLICE- Street-Level Insights from Camera Evidence.
.- Deep Learning-Based Infant Brain Tissue Segmentation using Attention-Gated U-Net.
.- BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation.
.- Point Cloud Fusion with Diffusion Models: An Integrated Pipeline for High-Quality Surround View Rendering.
.- Hierarchical Vector-Quantized Latents for Perceptual Low-Resolution Video Compression.
.- Multi-Query Person Retrieval on Edge Devices.
.- A Comprehensive Dataset for Underground Miner Detection in Diverse Scenario.
.- Measurement of Screen-Based Computer Work Duration via Web Camera Applying YOLO for Facial Landmark Detection.
.- Organoid Segmentation Using Phase Congruency and Persistent Homology.
.- Angle Based DTW for Large Vocabulary Sign Retrieval.
.- Deep Learning-Based Declouding of the Aurora Borealis.
.- Vision Embeddings and Their Role in Hallucination Vulnerabilities of Multimodal Large Language Models.
.- Enhancing Infrastructure Monitoring with Calibrated Vision Language Model Ensembles: A Graffiti Detection Case Study.
.- Uncertainty-Aware Remaining Lifespan Prediction from Images.
.- Exploratory Insights into Late-Fused Attribute Cues for RGB-based Military Vehicle Recognition.
.- ”Are We Going To Crash?”: The Effect of an AI Presence in User Experience during a VR Flight.
.- Evaluation of video augmentation effects and immersive experience in MR environments.
Zusammenfassung
This two-volume set constitutes the proceedings of the 20th International Symposium, ISVC 2025, held in Las Vegas, NV, USA, during November 17–19, 2025.
The 54 full papers and 18 poster papers were carefully reviewed and selected from 118 submissions. The papers cover the following topical sections:
Part I: Deep Learning; Computer Graphics; Motion and Tracking; Applications; Object Detection and Recognition; Medical Imaging, and Virtual Reality.
Part II: Segmentation; 3D; Recognition; Video Analysis and Event Recognition; Biometrics; Visualization, and Poster.
