Google
×
AllImagesVideosNews Maps Shopping Books
Search tools

Learning to reason over scene graphs: a case study of finetuning GPT-2 into a robot language model for grounded task planning

Frontiers
In this work, we investigate the applicability of a smaller class of large language models (LLMs), specifically GPT-2, in robotic task planning.
3 months ago

Researchers improve scene perception with innovative framework

Tech Xplore
Led by Prof. Liu Yong from the Hefei lnstitutes of Physical Science of the Chinese Academy of Sciences, researchers have proposed a novel...
4 months ago

Scene Graph Generation and its Application in Robotics

Towards Data Science
Scene graph generation is the process of generating scene graphs and a scene graph contains the visual understanding of an image in the form...
11 months ago

This AI Paper from China Introduces SGTR and SGTR+: An End-to-End CNN-Transformer-Based Scene Graph Generating Framework and Its Extension

MarkTechPost
This paper proposes a novel approach to address these challenges, leveraging the compositional property of scene graphs.
7 months ago

How An AI Understands Scenes: Panoptic Scene Graph Generation.

HackerNoon
But panoptic segmentation has advantages, such as it covers the full scene with background and has better accuracy compared to the coarse...
11 months ago

3D graphics programming in Java, Part 1: Java 3D

InfoWorld
Java 3D is near final release and has already created quite a stir in the Java graphics community. This month, Bill takes an in-depth look at the API and...
2 months ago

Interpreting relationships from images with world-leading accuracy – Fujitsu’s scene graph generation technology sets new standards for image recognition, recognizing the relationship between people, objects, and the environment to create a highly accurate

Fujitsu
Interpreting relationships from images with world-leading accuracy – Fujitsu's scene graph generation technology sets new standards for...
24 months ago

Deep Generative Probabilistic Graph Neural Networks for Scene Graph Generation

The Association for the Advancement of Artificial Intelligence
Abstract. We propose a new algorithm, called Deep Generative Probabilistic Graph Neural Networks (DG-PGNN), to generate a scene graph for an...
54 months ago

Meet Davidsonian Scene Graph: A Revolutionary AI Framework for Assessing Text-to-Image AI with Precision

MarkTechPost
Researchers have introduced the Davidsonian Scene Graph (DSG), an automatic QG/A framework inspired by formal semantics.
11 months ago

Long-form video representation learning (Part 3: Long-form egocentric video representation learning)

Towards Data Science
The first two blogs in this series described how different architectural motifs ranging from graph neural networks to sparse transformers addressed the...
4 months ago