Author name cluster

Xiaolin Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

Blur-Robust Detection via Feature Restoration: An End-to-End Framework for Prior-Guided Infrared UAV Target Detection

Xiaolin Wang
Houzhang Fang
Qingshan Li
Lu Wang
Yi Chang
Luxin Yan

Infrared unmanned aerial vehicle (UAV) target images often suffer from motion blur degradation caused by rapid sensor movement, significantly reducing contrast between target and background. Generally, detection performance heavily depends on the discriminative feature representation between target and background. Existing methods typically treat deblurring as a preprocessing step focused on visual quality, while neglecting the enhancement of task-relevant features crucial for detection. Improving feature representation for detection under blur conditions remains challenging. In this paper, we propose a novel Joint Feature-Domain Deblurring and Detection end-to-end framework, dubbed JFD³. We design a dual-branch architecture with shared weights, where the clear branch guides the blurred branch to enhance discriminative feature representation. Specifically, we first introduce a lightweight feature restoration network, where features from the clear branch serve as feature-level supervision to guide the blurred branch, thereby enhancing its distinctive capability for detection. We then propose a frequency structure guidance module that refines the structure prior from the restoration network and integrates it into shallow detection layers to enrich target structural information. Finally, a feature consistency self-supervised loss is imposed between the dual-branch detection backbones, driving the blurred branch to approximate the feature representations of the clear one. We also construct a benchmark, named IRBlurUAV, containing 30,000 simulated and 4,118 real infrared UAV target images with diverse motion blur. Extensive experiments on IRBlurUAV demonstrate that JFD³ achieves superior detection performance while maintaining real-time efficiency.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation

Xiaolin Wang
Guohao Sun
Xiu Fang
Jian Yang
Shoujin Wang

Point-of-interest (POI) recommendations can help users explore attractive locations, which is playing an important role in location-based social networks (LBSNs). In POI recommendations, the results are largely impacted by users' preferences. However, the existing POI methods model user and location almost separately, which cannot capture users' personal and dynamic preferences to location. In addition, they also ignore users' acceptance to distance/time of location. To overcome the limitations of the existing methods, we first introduce Knowledge Graph with temporal information (known as TKG) into POI recommendation, including both user and location with timestamps. Then, based on TKG, we propose a Spatial-Temporal Graph Convolutional Attention Network (STGCAN), a novel network that learns users' preferences on TKG by dynamically capturing the spatial-temporal neighbourhoods. Specifically, in STGCAN, we construct receptive fields on TKG to aggregate neighbourhoods of user and location respectively at each timestamp. And we measure the spatial-temporal interval as users' acceptance to distance/time with self-attention. Experiments on three real-world datasets demonstrate that the proposed model outperforms the state-of-the-art POI recommendation approaches.

PDF Details DOI

ICRA Conference 2013 Conference Paper

Automated laser-induced cell fusion based on microwell array

Xiaolin Wang
Shuxun Chen
Chi-wing Kong
Ronald A. Li
Dong Sun 0001

Engineering induced cell fusion is becoming a promising tool in novel therapeutic studies for treating various diseases. The majority of current in vitro cell fusion methods are based on random cell pairing with loose contact, which also needs large amounts of cells. In this paper, we present a robotically controlled laser-induced cell fusion approach based on the microwell array, which exhibits advantages of high selectivity and controllability. Optical tweezers and optical scissors are employed to achieve cell pairing and fusion, respectively. The specific cells are characterized and preselected with an on-chip isolation method prior to pairing. The paired cells are then transported, deposited, fused, and released at a predefined location with high spatiotemporal resolution. Experiments of fusion on individual pairs of human embryonic stem cells are performed to evaluate the performance of the proposed cell fusion tool.

Details

ICRA Conference 2012 Conference Paper

Automated parallel cell isolation and deposition using microwell array and optical tweezers

Xiaolin Wang
Xiao Yan 0003
Shuxun Chen
Dong Sun 0001

Isolation and deposition of specific live cells with the high spatio-temporal resolution from the heterogeneous mixtures are of critical importance to a wide range of biomedical applications. In this paper, we report a robot-assisted cell manipulation tool with optical tweezers based on a uniquely designed microwell array. The whole automatic manipulation includes the target cell recognition, isolation, transportation and deposition. The microwell array is designed based on microfluidics technology, which allows the passive hydrodynamic docking of cells. Image processing technique is used to recognize the target cells based on the cell size or fluorescence label. After recognition, the target cells can be levitated from the microwell, and then assembled by multiple optical traps in parallel. The optically trapped target cells are then transported and deposited to the desired location precisely. Experiments are performed to demonstrate the effectiveness of the proposed cell manipulation approach.

Details

ICRA Conference 2011 Conference Paper

Robot-assisted automatic cell sorting with combined optical tweezer and microfluidic chip technologies

Xiaolin Wang
Shuxun Chen
Dong Sun 0001

This paper presents a robot-assisted methodology that integrates optical tweezer and microfluidic chip technologies to realize automatic cell sorting from small sample population. The microfluidic chip used for cell sorter is designed and fabricated, and the flow environment within the microfluidic channel is investigated with simulation. Two image processing methods, depending on size and fluorescence label respectively, are used to recognize the target cells. With robotic manipulation of optical tweezers, the target cells can be moved to the desired area. Motions of optical tweezers are further analyzed for improvement of transportation efficiency. The relationship between the laser power and the cell maximum moving velocity is analyzed such that the robust cell sorting with as low power as possible can be achieved. Experiments on sorting yeast cells are performed to demonstrate the effectiveness of the proposed cell sorting approach.

Details