Human-Centric Image Captioning with Subject-Centered Spatial Understanding
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4337-4346
Abstract
No abstract availableFunding Information
- Beijing Major Science and Technology Project (Z251100008425023)
This publication has 15 references indexed in Scilit:
- DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models2026
- Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key2025
- VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models2025
- Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification2025
- MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI2024
- Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs2024
- Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID2024
- ImageInWords: Unlocking Hyper-Detailed Image Descriptions2024
- Direct Metric Optimization for Image Captioning through Reward-Weighted Augmented Data Utilization2024
- HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales2023