Researchers at Intel Labs, in collaboration with Xiamen University, have presented LiSA, the first semantic aware AI framework for highly accurate 3D visual localization. LiSA can leverage pre-trained semantic segmentation models to significantly improve state-of-the-art 3D visual localization accuracy, without introducing computational overhead during inference. LiSA was presented at CVPR 2024 as a highlight paper, an award given to the top 3.6% of conference papers.
-
-
Articles récents
- Multi-Modal Brand Agent: Connecting Visual Logos to Business Intelligence
- Building Efficient Multi-Modal AI Agents with Model Context Protocol (MCP)
- Intel Presents Novel Research at NAACL 2025
- Getting Started with Intel® Tiber™ AI Cloud
- AI Playground: Experience the Latest GenAI Software on AI PCs Powered by Intel® Arc™ Graphics
-
Neural networks news
Intel NN News
- Multi-Modal Brand Agent: Connecting Visual Logos to Business Intelligence
Identify brands from logos and retrieve business data in seconds. This AI agent links vision models […]
- Building Efficient Multi-Modal AI Agents with Model Context Protocol (MCP)
A deep dive into creating modular, specialized AI systems that rival large language models.
- Intel Presents Novel Research at NAACL 2025
Intel is proud to present four papers this year’s Annual Conference of the Nations of the […]
- Multi-Modal Brand Agent: Connecting Visual Logos to Business Intelligence
-