Call for Paper-CFP flyer downloading

This symposium has 8 tracks, with topics of interest included but not limited to:

Track 1: Foundational Visual Perception & Representation Learning

  • Low-level vision and image processing
  • Visual representation and feature learning
  • Unsupervised / self-supervised / semi-supervised learning
  • Metric learning and embedding models
  • Transfer learning and domain adaptation
  • Visual attention and saliency models
  • Lightweight and efficient visual models

Track 2: Generative AI & Visual Synthesis

  • Generative adversarial networks (GANs)
  • Diffusion models and transformer-based generation
  • Image, video, and 3D object generation
  • Text-to-image / text-to-video generation
  • Neural radiance fields (NeRF) and novel view synthesis
  • Image-to-image translation and editing
  • Content creation and digital human

Track 3: 3D Vision & Reconstruction

  • 3D point cloud processing and understanding
  • 3D object detection, segmentation, and tracking
  • Multi-view stereo and depth estimation
  • Surface reconstruction and geometric modeling
  • 3D scene understanding and layout estimation
  • RGB-D sensing and fusion
  • 3D-aware generative models

Track 4: Video Understanding & Action Recognition

  • Video classification and action recognition
  • Video object detection, tracking, and segmentation
  • Video captioning and retrieval
  • Video summarization and highlight detection
  • Activity analysis and behavior understanding
  • Event detection and anomaly detection
  • Multimedia analysis and understanding

Track 5: Multimodal Fusion & Cross-Modal Intelligence

  • Vision-language pre-training and alignment
  • Multimodal representation learning and fusion
  • Visual question answering (VQA) and reasoning
  • Cross-modal retrieval and generation
  • Multimodal large models and agents
  • Multimodal emotion and sentiment analysis

Track 6: Trustworthy AI & Visual Robustness

  • Adversarial robustness and defense
  • Fairness, accountability, and transparency
  • Privacy-preserving visual learning
  • Interpretability and explainable AI (XAI)
  • Out-of-distribution detection
  • Ethics and safety in computer vision

Track 7: Edge Intelligence & Embedded Vision

  • Model compression and acceleration
  • Embedded vision systems and hardware
  • Edge computing and distributed vision
  • Real-time visual perception on devices
  • Low-power vision and IoT applications
  • Autonomous perception on edge devices

Track 8: Medical Imaging & Biometric Analysis

  • Medical image segmentation and detection
  • Computer-aided diagnosis and prognosis
  • Biometric recognition (face, fingerprint, iris, etc.)
  • Multi-modal medical image fusion
  • Medical image generation and enhancement
  • Clinical applications and validation