Jintao Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jintao Huang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Dong Wang
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
2 shared publications - Ruochun Jin
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
2 shared publications - Yuanxi Peng
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
2 shared publications - Bojun Li
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
1 shared publication Cheng Zhu
1 shared publication- Huibin Tan
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3405-3413
VOMEL: Void-Aware Optimization for Multimodal Entity Linking
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3405-3413
Open AccessVOMEL: Void-Aware Optimization for Multimodal Entity Linking
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9363-9372
MoViS: Interactive 3D Human Motion Authoring via Zero-3D Visual Prompts
Generating spatially-aware 3D human motions from natural language remains a fundamental challenge, as text inherently lacks precise trajectory control. While recent methods condition generation on explicit 3D scenes to enforce physical grounding, they impose a severe human-computer interaction (HCI) bottleneck, demanding specialized 3D expertise and cumbersome user inputs. To democratize spatial control, we propose a paradigm shift: an interactive, zero-3D multimodal authoring framework named MoViS. MoViS empowers users to dictate complex spatial intent simply by drawing a 2D planar sketch (Visual Prompt) over a scene image, complemented by a text instruction. However, inferring 3D physical geometry from ambiguous 2D sketches presents extreme challenges in perspective scale and long-horizon intent drift. To overcome these, MoViS introduces a Physics-Grounded Cross-Modal Alignment mechanism, uniting 3D landmark distillation and continuous 2D perspective projection to embed true spatial awareness into a discrete generative backbone. Furthermore, we propose a cognitive-inspired Sketch-Driven Compositional Decoding strategy to robustly execute complex, multi-stage tasks. To catalyze this new paradigm, we construct IndoorViS, a large-scale multimodal dataset featuring 2,015 daily tasks across 1,173 diverse scenes. Extensive experiments demonstrate that MoViS strictly maintains the physical fidelity of explicit 3D-aware models while reducing human authoring overhead by over 90%, establishing a new standard for accessible and expressive embodied agent control.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9363-9372
Open AccessMoViS: Interactive 3D Human Motion Authoring via Zero-3D Visual Prompts
Generating spatially-aware 3D human motions from natural language remains a fundamental challenge, as text inherently lacks precise trajectory control. While recent methods condition generation on explicit 3D scenes to enforce physical grounding, they impose a severe human-computer interaction (HCI) bottleneck, demanding specialized 3D expertise and cumbersome user inputs. To democratize spatial control, we propose a paradigm shift: an interactive, zero-3D multimodal authoring framework named MoViS. MoViS empowers users to dictate complex spatial intent simply by drawing a 2D planar sketch (Visual Prompt) over a scene image, complemented by a text instruction. However, inferring 3D physical geometry from ambiguous 2D sketches presents extreme challenges in perspective scale and long-horizon intent drift. To overcome these, MoViS introduces a Physics-Grounded Cross-Modal Alignment mechanism, uniting 3D landmark distillation and continuous 2D perspective projection to embed true spatial awareness into a discrete generative backbone. Furthermore, we propose a cognitive-inspired Sketch-Driven Compositional Decoding strategy to robustly execute complex, multi-stage tasks. To catalyze this new paradigm, we construct IndoorViS, a large-scale multimodal dataset featuring 2,015 daily tasks across 1,173 diverse scenes. Extensive experiments demonstrate that MoViS strictly maintains the physical fidelity of explicit 3D-aware models while reducing human authoring overhead by over 90%, establishing a new standard for accessible and expressive embodied agent control.
- 28 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 325
Improving multimodal entity linking through modalities feature disentangling
- 28 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 325
Improving multimodal entity linking through modalities feature disentangling
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 960-969
Enhancing Multimodal Entity Linking via Distillation and Multimodal Large Language Models
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 960-969
Open AccessEnhancing Multimodal Entity Linking via Distillation and Multimodal Large Language Models