Overview
Logistics robots grasp objects using RGB recognition and point cloud pose estimation; assistants fuse language commands with scene geometry to execute complex tasks. Advancing from passive understanding to active perception, 3D multimedia analytics now drives autonomous systems, dexterous manipulation, and collaborative manufacturing.
Researchers have advanced 3D multimedia analytics across autonomous driving, robotic navigation, smart manufacturing, and logistics, where agents grasp, move, and inspect objects using 3D data. Beyond passive analysis, embodied systems demand active perception and interaction, pushing new challenges in sim-to-real transfer, affordance learning, and multimodal decision-making.
This workshop aims to:
- Convene state-of-the-art research in 3D multimedia analysis
- Address emerging challenges in multimodal 3D perception
- Establish benchmarks for both classic and embodied 3D tasks
- Showcase innovations in representation learning and interactive systems
- Demonstrate real-world 3D multimedia applications
- Introduce new datasets spanning static scenes to dynamic interactions
Submit Paper (Link TBD)
Call for Papers
We solicit original research and survey papers in (but not limited to) the following topics:
Generative Models
Generative Models for 3D Multimedia and 3D Multimedia Synthesis
Real-world Data
Generating 3D Multimedia from Real-world Data
Multimodal Analysis
3D Multimodal Analysis and Description
VR / AR
Multimedia Virtual/Augmented Reality
Search & Rec
3D Multimedia Search and Recommendation
3D Art & Culture
3D Multimedia Art, Entertainment and Culture
Mobile 3D
Mobile 3D Multimedia
Shape & Reconstruction
3D Shape Estimation and Reconstruction
Scene Understanding
3D Scene Understanding
Segmentation
3D Semantic Segmentation
Detection & Tracking
3D Object Detection and Tracking
Representation Learning
High-level Representation of 3D Multimedia Data
Robotics
3D Multimedia Data Understanding for Robotics
Embodied Interaction
Embodied 3D Scene Interaction and Manipulation