Yuehu Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuehu Liu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Beibei Wang
College of Artificial Intelligence, Xian Jiaotong University,Xian,China
2 shared publications - Sensen Wang
Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China
2 shared publications - Xiaohan Wang
Tencent PCG
2 shared publications Bin Tian
The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication- Chenghong Wang
Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
1 shared publication - Chi Zhang
Xi’an Jiaotong University
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 787-795
BiOMamba: Mamba-based Forward-Then-Backward Temporal Modeling for Online Action Detection and Anticipation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 787-795
Open AccessBiOMamba: Mamba-based Forward-Then-Backward Temporal Modeling for Online Action Detection and Anticipation
- Open Access
- 14 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 194-201
Online Action Detection via Temporal Dependency Modeling with Semantics Embedding
- 14 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 194-201
Open AccessOnline Action Detection via Temporal Dependency Modeling with Semantics Embedding
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5035-5040
Learning Object Relation Graph and Goal-Aware Policy For Visual Room Rearrangement
Embodied AI, where agents accomplish specific tasks through interaction with their surrounding environment, is attracting attention in the community. As a more comprehensive and practical embodied task, visual room rearrangement aims to rearrange the initially misplaced objects in a room to the target configuration. In this task, the misplaced targets are mostly small objects that are difficult to locate, and there is no indication of which object needs to be rearranged in sensory input. Direct search for small and unknown targets poses a challenge. Previous works tend to directly incorporate sensory input into a reward-based framework. These methods do not learn the relationships between objects and infer which objects need to be rearranged, resulting in low performance. Understanding the scene structure and reasoning task goals can enable agents to rearrange targets more efficiently. In this paper, we propose a receptacle-target relation graph, which considers the spatial relationship between target objects and the receptacle objects appearing around them, enabling agents to understand the environment. Furthermore, we also propose a target reasoning network to explicitly predict the target object. Finally, our goal-aware policy can plan a series of actions based on their understanding of the task goal. Extensive compmethodarative and ablation experiments were conducted on the AI2Thor platform, demonstrating the effectiveness of our method.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5035-5040
Learning Object Relation Graph and Goal-Aware Policy For Visual Room Rearrangement
Embodied AI, where agents accomplish specific tasks through interaction with their surrounding environment, is attracting attention in the community. As a more comprehensive and practical embodied task, visual room rearrangement aims to rearrange the initially misplaced objects in a room to the target configuration. In this task, the misplaced targets are mostly small objects that are difficult to locate, and there is no indication of which object needs to be rearranged in sensory input. Direct search for small and unknown targets poses a challenge. Previous works tend to directly incorporate sensory input into a reward-based framework. These methods do not learn the relationships between objects and infer which objects need to be rearranged, resulting in low performance. Understanding the scene structure and reasoning task goals can enable agents to rearrange targets more efficiently. In this paper, we propose a receptacle-target relation graph, which considers the spatial relationship between target objects and the receptacle objects appearing around them, enabling agents to understand the environment. Furthermore, we also propose a target reasoning network to explicitly predict the target object. Finally, our goal-aware policy can plan a series of actions based on their understanding of the task goal. Extensive compmethodarative and ablation experiments were conducted on the AI2Thor platform, demonstrating the effectiveness of our method.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2838-2846
Generating Explanations for Embodied Action Decision from Visual Observation
Getting trust is crucial for embodied agents (such as robots and autonomous vehicles) to collaborate with human beings, especially non-experts. The most direct way for mutual understanding is through natural language explanation. Existing researches consider generating visual explanations for object recognition, while the exploration of explaining embodied decisions remains vacant. In this paper, we study generating action decisions and explanations based on visual observation. Distinct to explanations for recognition, justifying an action needs to show why it's better than other actions. Besides, the understanding of scene structure is required since the agent needs to interact with the environment (e.g. navigation, moving objects). We introduce a new dataset THOR-EAE (Embodied Action Explanation) collected based on AI2-THOR simulator. The dataset consists of over 840,000 egocentric images of indoor embodied observation which are annotated with the optimal action labels and explanation sentences. An explainable decision-making criterion is developed considering scene layout and action attributes for efficient annotation. We propose a graph action justification model, exploiting graph neural networks for obstacle-surroundings relations representation and justifying the actions under the guidance of decision results. Experimental results on THOR-EAE dataset showcase its challenge and the effectiveness of the proposed method.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2838-2846
Open AccessGenerating Explanations for Embodied Action Decision from Visual Observation
Getting trust is crucial for embodied agents (such as robots and autonomous vehicles) to collaborate with human beings, especially non-experts. The most direct way for mutual understanding is through natural language explanation. Existing researches consider generating visual explanations for object recognition, while the exploration of explaining embodied decisions remains vacant. In this paper, we study generating action decisions and explanations based on visual observation. Distinct to explanations for recognition, justifying an action needs to show why it's better than other actions. Besides, the understanding of scene structure is required since the agent needs to interact with the environment (e.g. navigation, moving objects). We introduce a new dataset THOR-EAE (Embodied Action Explanation) collected based on AI2-THOR simulator. The dataset consists of over 840,000 egocentric images of indoor embodied observation which are annotated with the optimal action labels and explanation sentences. An explainable decision-making criterion is developed considering scene layout and action attributes for efficient annotation. We propose a graph action justification model, exploiting graph neural networks for obstacle-surroundings relations representation and justifying the actions under the guidance of decision results. Experimental results on THOR-EAE dataset showcase its challenge and the effectiveness of the proposed method.
- Top Cited Papers
- 13 March 2019
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 4 (28)
Parallel testing of vehicle intelligence via virtual-real interaction
A closed-loop parallel testing system implements more challenging tests to accelerate evaluation and development of autonomous vehicles.
- 13 March 2019
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 4 (28)
Top Cited PapersParallel testing of vehicle intelligence via virtual-real interaction
A closed-loop parallel testing system implements more challenging tests to accelerate evaluation and development of autonomous vehicles.
- Open Access
- 1 July 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4225 (19457871) , 1-4
3D facial mesh detection using geometric saliency of surface
This paper proposes a 3D facial mesh detection algorithm based on the geometric saliency of surface. Specifically, the geometric saliency of each vertex on 3D triangle mesh is measured by the combination of Gaussian-weighted curvature and spin-image correlation. Salient vertices with similar properties are clustered into regions on the saliency map, and represented as nodes by the graph model. To detect a 3D facial mesh, initialization and registration steps are applied to match each triangle in the graph model with a reference graph, corresponding to a 3D reference facial mesh. Furthermore, the match error between the graph model of the testing 3D mesh and the reference facial mesh is computed to classify face and non-face meshes. Experimental results demonstrate that the proposed algorithm is effective to detect 3D facial meshes and robust to facial expressions and geometric noises.
- 1 July 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4225 (19457871) , 1-4
Open Access3D facial mesh detection using geometric saliency of surface
This paper proposes a 3D facial mesh detection algorithm based on the geometric saliency of surface. Specifically, the geometric saliency of each vertex on 3D triangle mesh is measured by the combination of Gaussian-weighted curvature and spin-image correlation. Salient vertices with similar properties are clustered into regions on the saliency map, and represented as nodes by the graph model. To detect a 3D facial mesh, initialization and registration steps are applied to match each triangle in the graph model with a reference graph, corresponding to a 3D reference facial mesh. Furthermore, the match error between the graph model of the testing 3D mesh and the reference facial mesh is computed to classify face and non-face meshes. Experimental results demonstrate that the proposed algorithm is effective to detect 3D facial meshes and robust to facial expressions and geometric noises.