MIRU2024

何か投稿ネタはないか？

領域A：幾何学的解析，光学的解析，3次元解析 | Area A: Geometric analysis, optical analysis, 3D analysis

Camera, geometry, and photometry

Computational imaging

Physics-based vision and graphics

Registration, pose estimation, and tracking

3D from a single image and shape-from-x

3D shape modeling, processing, and synthesis

3D from multi-view and sensors

領域B：パターン認識，機械学習，深層学習 | Area B: Pattern recognition, machine learning, deep learning

Datasets, training, and evaluation

Deep learning (architectures, generative models, deep reinforcement learning, geometric deep learning, etc.)

General machine learning (active learning, clustering, online learning, ranking, reinforcement learning, un/semi/self-supervised learning, time series analysis, etc.)

Learning theory (Bayesian methods, graphical models, statistical learning theory, etc.)

Optimization (convex / non-convex optimization, matrix / tensor methods, stochastic, online, non-smooth, composite, etc.)

Representation learning and feature extraction

Transfer, low-shot, continual, and long-tail learning

Trustworthy machine learning (accountability, causality, fairness, privacy, robustness, etc.)

領域C：画像/映像/マルチメディア処理 | Area C: Image/video/multimedia processing

Action and event understanding

Categorization, segmentation, and shape analysis

Image / video analysis, retrieval, and understanding

Image / video synthesis

Low-level vision and signal processing

Multimedia

Object detection, matching, and tracking

Vision and language

領域D：応用 | Area D: Application

Autonomous driving and ITS

Biometrics

Cloud, web, and social media

Document analysis and understanding

Efficient, scalable, and realtime processing

Human sensing (faces, gestures, pose, shape, etc.)

Industry and manufacturing

Life (sports, agriculture / forestry / fishery, civil engineering, commerce, fashion, food, home, etc.)

Medical / biological vision and cell microscopy

Robot vision and embodied vision

Scene analysis and understanding

XR and HCI