Bao Huynh Thai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bao Huynh Thai has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Anh-Duong Tran
University of Information Technology
2 shared publications - Dat Phan Thanh
University of Information Technology
2 shared publications - Dinh-Khoi Vo
University of Science
2 shared publications - Duc-Vu Nguyen
University of Information Technology
2 shared publications - Hien-Long Le-Hoang
University of Information Technology
2 shared publications - Hoang Tran Van
University of Information Technology
2 shared publications
Latest Publications
- 12 August 2026
- Published by Springer Nature
- p. 1-11
FRED: Unified Multimodal Fusion and Dynamic Temporal Reasoning with Semantic Query Expansion and Exclusionary Search
- 12 August 2026
- Published by Springer Nature
- p. 1-11
FRED: Unified Multimodal Fusion and Dynamic Temporal Reasoning with Semantic Query Expansion and Exclusionary Search
- 3 September 2025
- Published by Elsevier in Computers & Graphics
- Vol. 132
SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)
- 3 September 2025
- Published by Elsevier in Computers & Graphics
- Vol. 132
SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)
- Open Access
SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)
Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addition, ROOMELSA includes over 1,600 apartment scenes, nearly 5,200 rooms, and more than 44,000 targeted queries. Empirically, while coarse object retrieval is largely solved, only one top-performing model consistently ranked the correct match first across nearly all test cases. Notably, a lightweight CLIP-based model also performed well, although it struggled with subtle variations in materials, part structures, and contextual cues, resulting in occasional errors. These findings highlight the importance of tightly integrating visual and language understanding. By bridging the gap between scene-level grounding and fine-grained 3D retrieval, ROOMELSA establishes a new benchmark for advancing robust, real-world 3D recognition systems.
Open AccessSHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)
Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addition, ROOMELSA includes over 1,600 apartment scenes, nearly 5,200 rooms, and more than 44,000 targeted queries. Empirically, while coarse object retrieval is largely solved, only one top-performing model consistently ranked the correct match first across nearly all test cases. Notably, a lightweight CLIP-based model also performed well, although it struggled with subtle variations in materials, part structures, and contextual cues, resulting in occasional errors. These findings highlight the importance of tightly integrating visual and language understanding. By bridging the gap between scene-level grounding and fine-grained 3D retrieval, ROOMELSA establishes a new benchmark for advancing robust, real-world 3D recognition systems.