Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation

Source

arXiv

arxiv.org/abs/2608.05026v1

Read the source

Source

Plain-Language Brief

The paper presents ArtAnno, a system that uses a bidirectional human-AI augmentation (BiHAA) framework to improve the efficiency of artwork annotation. This system helps experts by suggesting semantic labels and learns from their input to enhance its performance over time.

What the Document Says

  • ArtAnno is an artwork annotation system that uses a bidirectional human-AI augmentation (BiHAA) framework.
  • The BiHAA framework consists of a Proactive Agentic Support Module and an Interaction-Driven Evolution Module.
  • The Proactive Agentic Support Module helps experts by suggesting semantic labels.
  • The Interaction-Driven Evolution Module learns from the input provided by experts to enhance its performance over time.
  • The system is designed to improve annotation efficiency, enable knowledge accumulation, and reduce the effort of information seeking and verification for annotators with limited domain expertise.

Key Concepts Mentioned

  • ArtAnno
  • Bidirectional Human-AI Augmentation (BiHAA)
  • Proactive Agentic Support Module
  • Interaction-Driven Evolution Module

Claims Made by the Document

  • The proposed framework and system improve annotation efficiency.
  • The system enables knowledge accumulation.
  • The system reduces the effort of information seeking and verification for annotators with limited domain expertise.

Evidence Used

  • Evaluation through a user study and two case studies

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

High-quality annotation of artworks is essential for computational art research, yet extracting implicit semantics remains challenging due to the reliance on culturally grounded meanings and deep contextual knowledge behind the images. Current AI-assisted annotation tools often lack assistance or rely on one-way workflows where experts have to perform extra manual calibrations to improve AI models, resulting in limited efficiency. To address this, we propose Bidirectional Human-AI Augmentation(BiHAA), a closed-loop framework in which skills and domain knowledge base evolve through real-time interaction and bidirectional HAI augmentation. Informed by a formative study with 20 artwork annotators from different backgrounds, we implement this framework in ArtAnno, an artwork annotation system driven by a multi-agent architecture. The system includes a Proactive Agentic Support Module, where AI augments humans through semantic mining and label suggestion, and an Interaction-Driven Evolution Module, where human expertise continuously enhances the AI through distilling annotation trajectories into reusable experience. Evaluation through a user study and two case studies demonstrates that our framework and system improve annotation efficiency, enable knowledge accumulation, and reduce the effort of information seeking and verification for annotators with limited domain expertise. We conclude by discussing broader implications and future directions.