SOURCE-LINKED INTELLIGENCE

Human-Centric Image Captioning with Subject-Centered Spatial Understanding

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural hallucinations in human-centric scenarios. Accurately modeling human subjects is foundational for critical downstream applications, such as accurate avatar/video/image generation and fine-grained human action understanding. However, these tasks require highly precise subject-centered spatial grounding, such as distinguishing egocentric left/right laterality and maintaining correct anatomical-object bindings. Although catastrophic for structural integ

Read original source ↗ Open in workspace

recordType

paper

region

Global