LLLiyuan Li

Liyuan Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Liyuan Li has a total of 55 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks

    by Mei Chee Leong, Ying Gu, Hui Li Tan, Liyuan Li, Nancy F. Chen

  • Open Access

    Contextualized Visual Storytelling for Conversational Chatbot in Education

    by Hui Li Tan, Ying Gu, Liyuan Li, Mei Chee Leong, Nancy F. Chen


  • A New Perspective on Wise Proactivity: Configural Effect of Proactivity Process

    by Liyuan Li, Xiangyu Gao, Xiaoming Zheng

    Proactivity literature has come to realize that employee proactivity is a process including a set of actions rather than a one-off action (e.g., Bindl et al., 2012; Parker et al., 2010). We provide...

  • Towards a Programming-Free Robotic System for Assembly Tasks Using Intuitive Interactions

    by Nicolas Gauthier, Wenyu Liang, Qianli Xu, Fen Fang, Liyuan Li, Ruihan Gao, Yan Wu, Joo Hwee Lim


  • Open Access

    6D Pose Estimation with Correlation Fusion

    by Yi Cheng, Hongyuan Zhu, Ying Sun, Cihan Acar, Wei Jing, Yan Wu, Liyuan Li, Cheston Tan, Joo-Hwee Lim

    6D object pose estimation is widely applied in robotic tasks such as grasping and manipulation. Prior methods using RGB-only images are vulnerable to heavy occlusion and poor illumination, so it is important to complement them with depth information. However, existing methods using RGB-D data cannot adequately exploit consistent and complementary information between RGB and depth modalities. In this paper, we present a novel method to effectively consider the correlation within and across both modalities with attention mechanism to learn discriminative and compact multi-modal features. Then, effective fusion strategies for intra- and inter-correlation modules are explored to ensure efficient information flow between RGB and depth. To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation. The experimental results show that our method can achieve the state-of-the-art performance on LineMOD and YCB-Video dataset. We also demonstrate that the proposed method can benefit a real-world robot grasping task by providing accurate object pose estimation.

  • Open Access

    Neural correlates of retrieval-based enhancement of autobiographical memory in older adults

    by Qianli Xu, Jiayi Zhang, Joanes Grandjean, Cheston Tan, Vigneshwaran Subbaraju, Liyuan Li, Kuan Jin Lee, Po-Jang Hsieh, Joo-Hwee Lim

    Lifelog photo review is considered to enhance the recall of personal events. While a sizable body of research has explored the neural basis of autobiographical memory (AM), there is limited neural evidence on the retrieval-based enhancement effect on event memory among older adults in the real-world environment. This study examined the neural processes of AM as was modulated by retrieval practice through lifelog photo review in older adults. In the experiment, blood-oxygen-level dependent response during subjects’ recall of recent events was recorded, where events were cued by photos that may or may not have been exposed to a priori retrieval practice (training). Subjects remembered more episodic details under the trained relative to non-trained condition. Importantly, the neural correlates of AM was exhibited by (1) dissociable cortical areas related to recollection and familiarity, and (2) a positive correlation between the amount of recollected episodic details and cortical activation within several lateral temporal and parietal regions. Further analysis of the brain activation pattern at a few regions of interest within the core remember network showed a training_condition × event_detail interaction effect, suggesting that the boosting effect of retrieval practice depended on the level of recollected event details.


  • Single-Image Dehazing via Compositional Adversarial Network

    by Hongyuan Zhu, Yi Cheng, Xi Peng, Joey Tianyi Zhou, Zhao Kang, Shijian Lu, Zhiwen Fang, Liyuan Li, Joo-Hwee Lim

    Single-image dehazing has been an important topic given the commonly occurred image degradation caused by adverse atmosphere aerosols. The key to haze removal relies on an accurate estimation of global air-light and the transmission map. Most existing methods estimate these two parameters using separate pipelines which reduces the efficiency and accumulates errors, thus leading to a suboptimal approximation, hurting the model interpretability, and degrading the performance. To address these issues, this article introduces a novel generative adversarial network (GAN) for single-image dehazing. The network consists of a novel compositional generator and a novel deeply supervised discriminator. The compositional generator is a densely connected network, which combines fine-scale and coarse-scale information. Benefiting from the new generator, our method can directly learn the physical parameters from data and recover clean images from hazy ones in an end-to-end manner. The proposed discriminator is deeply supervised, which enforces that the output of the generator to look similar to the clean images from low-level details to high-level structures. To the best of our knowledge, this is the first end-to-end generative adversarial model for image dehazing, which simultaneously outputs clean images, transmission maps, and air-lights. Extensive experiments show that our method remarkably outperforms the state-of-the-art methods. Furthermore, to facilitate future research, we create the HazeCOCO dataset which is currently the largest dataset for single-image dehazing.


  • A Probabilistic Model of Social Working Memory for Information Retrieval in Social Interactions

    by Liyuan Li, Qianli Xu, Tian Gan, Cheston Tan, Joo-Hwee Lim

    Social working memory (SWM) plays an important role in navigating social interactions. Inspired by studies in psychology, neuroscience, cognitive science, and machine learning, we propose a probabilistic model of SWM to mimic human social intelligence for personal information retrieval (IR) in social interactions. First, we establish a semantic hierarchy as social long-term memory to encode personal information. Next, we propose a semantic Bayesian network as the SWM, which integrates the cognitive functions of accessibility and self-regulation. One subgraphical model implements the accessibility function to learn the social consensus about IR-based on social information concept, clustering, social context, and similarity between persons. Beyond accessibility, one more layer is added to simulate the function of self-regulation to perform the personal adaptation to the consensus based on human personality. Two learning algorithms are proposed to train the probabilistic SWM model on a raw dataset of high uncertainty and incompleteness. One is an efficient learning algorithm of Newton's method, and the other is a genetic algorithm. Systematic evaluations show that the proposed SWM model is able to learn human social intelligence effectively and outperforms the baseline Bayesian cognitive model. Toward real-world applications, we implement our model on Google Glass as a wearable assistant for social interaction.


  • Open Access

    Enhancing Social Interaction with Seamless Face Recognition on Google Glass

    by Shue-Ching Chia, Bappaditya Mandal, Qianli Xu, Liyuan Li, Joo-Hwee Lim

    Wearable devices offer immense opportunities in both consumer and enterprise domains due to the hands-free interaction modality and the ability to provide information in real-time. However, due to hardware limitations, it presents a notable challenge to complex applications that have stringent demands on computational efficiency. Leveraging on the computing power of a connected mobile device, we propose a new multi-threaded asynchronous structure to implement opportunistic multi-tasking. We demonstrate an application of the structure for seamless face recognition for social interactions. The experimental studies show that the proposed structure can achieve better performance than a sequential synchronous one. The proposed method can be extended to similar applications in wearable devices.


  • The effect of repetition priming on spatial memory during backtracking in a novel environment

    by Michal Mukawa, Cheston Tan, Joo-Hwee Lim, Qianli Xu, Liyuan Li

    During wayfinding in a novel environment, we encounter many new places. Some of those places are encoded by our spatial memory. But how does the human brain “decides” which locations are more important than others, and how do backtracking and repetition priming enhances memorization of these scenes? In this work, we explore how backtracking improves encoding of encountered locations. We also check whether repetition priming helps with further memory enhancement. We recruited 20 adults. Each participant was guided through an unfamiliar indoor environment. The participants were instructed to remember the path, as they would need to backtrack by themselves. Two groups were defined: the first group performed a spatial memory test at the goal destination and after backtracking; the second group performed the test only after backtracking. The mean spatial memory scores of the first group improved significantly after backtracking: from 49.8 to 60.8 %. The score of the second group was 62 %. No difference was found in performance between the first group and the second group. Backtracking alone significantly improves spatial memory of visited places. Surprisingly, repetition priming does not further enhance memorization of these places. This result may suggest that spatial reasoning causes significant cognitive load that thwarts further improvement of spatial memory of locations.