Ruiping Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ruiping Wang has a total of 117 co-authors. Here are the top co-authors by number of shared publications:
- Xilin Chen
Institute of Computing Technology, Chinese Academy of Sciences
36 shared publications - Shiguang Shan
Institute of Computing Technology, Chinese Academy of Sciences
27 shared publications Xilin Chen
13 shared publications- Haomiao Liu
Jilin University, College of Computer Science and Technology, No. 2699 Qianjin Street, Changchun, Jilin province, 130012, China; Jilin University, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, No. 2699 Qianjin Street, Changchun, Jilin province, 130012, China
4 shared publications Shiguang Shan
4 shared publications- Shishi Qiao
College of Electronic Engineering, Ocean University of China, Qingdao, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13512-13521
Think with Intent: Proactively Resolving User Intent in Visual Dialogue via Tool-aware CoT Reasoning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13512-13521
Open AccessThink with Intent: Proactively Resolving User Intent in Visual Dialogue via Tool-aware CoT Reasoning
- 1 October 2026
- Published by Springer Nature
- p. 59-76
Abstract the Layout, Focus the Detail: A Dual-Granularity Representation Framework for Zero-Shot 3D Visual Grounding
- 1 October 2026
- Published by Springer Nature
- p. 59-76
Abstract the Layout, Focus the Detail: A Dual-Granularity Representation Framework for Zero-Shot 3D Visual Grounding
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 12096-12103
GAS-Robo: Converting Scene Into a Grid-Action Space for LLM-Driven Open-Ended Robotic Manipulation
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 12096-12103
GAS-Robo: Converting Scene Into a Grid-Action Space for LLM-Driven Open-Ended Robotic Manipulation
- 12 September 2026
- Published by Springer Nature
- p. 243-260
STEP: Spatial Thinking and Egocentric Pointing for Embodied Instruction Following
- 12 September 2026
- Published by Springer Nature
- p. 243-260
STEP: Spatial Thinking and Egocentric Pointing for Embodied Instruction Following
- 28 July 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 208, 123-128
Decoupled gradient-guided stratification for resource-efficient multi-modal data pruning
- 28 July 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 208, 123-128
Decoupled gradient-guided stratification for resource-efficient multi-modal data pruning
- Top Cited Papers
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (7) , 8547-8566
A Survey on Interpretability in Visual Recognition
Visual recognition models have achieved unprecedented success in various tasks. While researchers aim to understand the underlying mechanisms of these models, the growing demand for deployment in safety-critical areas like autonomous driving and medical diagnostics has accelerated the development of eXplainable AI (XAI). Distinct from generic XAI, visual recognition XAI is positioned at the intersection of vision and language, which represent the two most fundamental human modalities and form the cornerstones of multimodal intelligence. This paper provides a systematic survey of XAI in visual recognition by establishing a multi-dimensional taxonomy from a human-centered perspective based on intent, object, presentation, and methodology. Beyond categorization, we summarize critical evaluation desiderata and metrics, conducting an extensive qualitative assessment across different categories and demonstrating quantitative benchmarks within specific dimensions. Furthermore, we explore the interpretability of Multimodal Large Language Models and practical applications, identifying emerging trends and opportunities. By synthesizing these diverse perspectives, this survey provides an insightful roadmap to inspire future research on the interpretability of visual recognition models.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (7) , 8547-8566
Top Cited PapersA Survey on Interpretability in Visual Recognition
Visual recognition models have achieved unprecedented success in various tasks. While researchers aim to understand the underlying mechanisms of these models, the growing demand for deployment in safety-critical areas like autonomous driving and medical diagnostics has accelerated the development of eXplainable AI (XAI). Distinct from generic XAI, visual recognition XAI is positioned at the intersection of vision and language, which represent the two most fundamental human modalities and form the cornerstones of multimodal intelligence. This paper provides a systematic survey of XAI in visual recognition by establishing a multi-dimensional taxonomy from a human-centered perspective based on intent, object, presentation, and methodology. Beyond categorization, we summarize critical evaluation desiderata and metrics, conducting an extensive qualitative assessment across different categories and demonstrating quantitative benchmarks within specific dimensions. Furthermore, we explore the interpretability of Multimodal Large Language Models and practical applications, identifying emerging trends and opportunities. By synthesizing these diverse perspectives, this survey provides an insightful roadmap to inspire future research on the interpretability of visual recognition models.
- 15 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12301-12308
FreeMask3D: Zero-Shot Point Cloud Instance Segmentation Without 3D Training
Point cloud instance segmentation is crucial for 3D scene understanding in robotics. However, existing methods heavily rely on learning-based approaches that require large amounts of annotated 3D data, resulting in high annotation costs. Therefore, developing cost-effective and data-efficient solutions is essential. To this end, we propose FreeMask3D, a novel approach that achieves 3D point cloud instance segmentation without requiring any 3D annotation or additional training. Our method consists of two main steps: instance localization and instance recognition. For instance localization, we leverage pre-trained 2D instance segmentation models to perform instance segmentation on corresponding RGB-D images. These results are then mapped to 3D space and fused across frames to generate the final 3D instance masks. For instance recognition, the OpenSem module infers the category of each instance by leveraging the generalization capabilities of cross-modal large models, such as CLIP, to enable open-vocabulary semantic recognition. Experiments and ablation studies on four challenging benchmarks—ScanNetv2, ScanNet200, S3DIS, and Replica—demonstrate that FreeMask3D achieves competitive or superior performance compared to state-of-the-art methods, despite without 3D supervision. Qualitative results highlight its open-vocabulary capabilities based on color, affordance, or uncommon phrase description.
- 15 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12301-12308
FreeMask3D: Zero-Shot Point Cloud Instance Segmentation Without 3D Training
Point cloud instance segmentation is crucial for 3D scene understanding in robotics. However, existing methods heavily rely on learning-based approaches that require large amounts of annotated 3D data, resulting in high annotation costs. Therefore, developing cost-effective and data-efficient solutions is essential. To this end, we propose FreeMask3D, a novel approach that achieves 3D point cloud instance segmentation without requiring any 3D annotation or additional training. Our method consists of two main steps: instance localization and instance recognition. For instance localization, we leverage pre-trained 2D instance segmentation models to perform instance segmentation on corresponding RGB-D images. These results are then mapped to 3D space and fused across frames to generate the final 3D instance masks. For instance recognition, the OpenSem module infers the category of each instance by leveraging the generalization capabilities of cross-modal large models, such as CLIP, to enable open-vocabulary semantic recognition. Experiments and ablation studies on four challenging benchmarks—ScanNetv2, ScanNet200, S3DIS, and Replica—demonstrate that FreeMask3D achieves competitive or superior performance compared to state-of-the-art methods, despite without 3D supervision. Qualitative results highlight its open-vocabulary capabilities based on color, affordance, or uncommon phrase description.
- 29 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Learning interpretable binary codes via semantic alignment for customized image retrieval
- 29 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Learning interpretable binary codes via semantic alignment for customized image retrieval
- 17 July 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 197, 51-57
Cross-Domain Few-Shot 3D Point Cloud Semantic Segmentation
- 17 July 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 197, 51-57
Cross-Domain Few-Shot 3D Point Cloud Semantic Segmentation
- 27 June 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (10) , 6813-6831
Generic Scene Graph Generation Model with Hierarchical Prompt Learning
- 27 June 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (10) , 6813-6831
Generic Scene Graph Generation Model with Hierarchical Prompt Learning