Contextual object detection with multimodal large language models

• Main Authors: Zang, Yuhang, Li, Wei, Han, Jun, Zhou, Kaiyang, Loy, Chen Change
• Other Authors: College of Computing and Data Science
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Image segmentation; Object detection
• Online Access: https://hdl.handle.net/10356/181063
• Institution: Nanyang Technological University

Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual...