Arrow Research search

Author name cluster

Weiwei Chen

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.

8 papers
2 author rows

Possible papers

8

EAAI Journal 2026 Journal Article

A robust zero-shot framework based on adaptive illumination perception and trichromatic calibration for extreme low-light image enhancement

  • Xuan Li
  • Zhaoming Feng
  • Weiwei Chen
  • Guomin Zhang
  • Yifan Ding
  • Li Cheng

Zero-shot low-light image enhancement methods eliminate the dependency on annotated data while demonstrating strong generalization capabilities. However, existing zero-shot methods fail to effectively handle extreme low-light conditions, resulting in insufficient brightness, over-exposure and color distortion. To address these issues, we propose a robust zero-shot framework based on adaptive illumination perception and trichromatic calibration for extreme low-light image enhancement, termed Zero-IPTC. In the proposed framework, an adaptive illumination perception network is designed to estimate enhancement curves by using asymmetric skip connections and hybrid attention modules. These structures endow the network with stronger representational power to flexibly recover details even under extreme illumination variations. Furthermore, we propose a trichromatic calibration mechanism to optimize the enhancement curves by modeling the inter-channel contrast relationships. The mechanism can significantly improve the color fidelity. Extensive experiments under diverse illumination conditions demonstrate that the proposed framework achieves state-of-the-art performance, achieving an average Naturalness Image Quality Evaluator (NIQE) score of 3. 04 and Lightness-Order-Error (LOE) score of 391. 2 across four benchmark datasets. The framework also showcases its adaptability in security surveillance and autonomous driving scenarios.

Details DOI

JBHI Journal 2026 Journal Article

A VR-based Automated Strabismus Diagnosis System with Progressive Semi-Supervised Learning

  • Dehui Qiu
  • Bowei Ma
  • Ze Xiong
  • Yuhao Wang
  • Liguo Deng
  • Longfei Zhou
  • Xiaojie Cao
  • Weiwei Chen

Strabismus is a prevalent ocular disorder that can impair visual development and cause psychological issues if not diagnosed early. Conventional clinical diagnosis primarily relies on the prism cover test (PCT), which is subjective, requires patient cooperation, and lacks standardization. Recent advances in virtual reality (VR) and deep learning offer promising solutions for automated and standardized diagnosis. However, practical deployment faces three key challenges: realistic VR simulation of clinical exams, addressing image degradation (reflections/occlusions) with limited annotated data, and precise quantification of ocular deviations. In this study, we propose a novel VR-based automated strabismus diagnosis system by leveraging semi-supervised deep learning, and introduce a new clinical dataset, TongRenD. The framework incorporates five standardized clinical examination scenarios within a VR environment to ensure diagnostic consistency. We introduce ProgNet: an uncertainty-guided progressive semi-supervised segmentation network that integrates a Prototype-based Feature Representation Module (PFRM) to enhance robustness against visual noise and distortions under limited annotations. A dedicated 3D deviation estimation algorithm further enables accurate strabismus classification and angular measurement. Extensive experiments on the TongRenD and TEyeD datasets demonstrate that ProgNet outperforms state-of-the-art methods in segmentation accuracy. Clinical validation confirms that our system achieves high consistency with expert assessments, providing a standardized, non-invasive, and reliable solution for strabismus diagnosis.

Details DOI

AAAI Conference 2025 Conference Paper

Evolutionary Reinforcement Learning with Parameterized Action Primitives for Diverse Manipulation Tasks

  • Xianxu Qiu
  • Haiming Huang
  • Weiwei Chen
  • Qiuzhen Lin
  • Wei-Neng Chen
  • Fuchun Sun

Reinforcement learning (RL) has shown promising performance in tackling robotic manipulation tasks (RMTs), which require learning a prolonged sequence of manipulation actions to control robots efficiently. However, most RL algorithms often suffer from two problems when solving RMTs: inefficient exploration due to the extremely large action space and catastrophic forgetting due to the poor sampling efficiency. To alleviate these problems, this paper introduces an Evolutionary Reinforcement Learning algorithm with parameterized Action Primitives, called ERLAP, which combines the advantages of an evolutionary algorithm (EA) and hierarchical RL (HRL) to solve diverse RMTs. A library of heterogeneous action primitives is constructed in HRL to enhance the exploration efficiency of robots and dual populations with new evolutionary operators are run in EA to optimize these primitive sequences, which can diversify the distribution of replay buffer and avoid catastrophic forgetting. The experiments show that ERLAP outperforms four state-of-the-art RL algorithms in simulated RMTs with dense rewards and can effectively avoid catastrophic forgetting in a set of more challenging simulated RMTs with sparse rewards.

PDF Details DOI

YNICL Journal 2024 Journal Article

Functional network reorganization after endovascular thrombectomy in patients with anterior circulation stroke

  • Tongyue Li
  • Jiaona Xu
  • Luoyu Wang
  • Kang Xu
  • Weiwei Chen
  • Liqing Zhang
  • Guozhong Niu
  • Yu Zhang

BACKGROUND: Endovascular thrombectomy has been confirmed to be an effective therapy for acute ischemic stroke (AIS). However, how functional brain networks reorganize after restoration of blood supply in AIS patients, and whether the degree of reperfusion associates with functional network changes remains unclear. METHODS: Resting-state fMRI data were collected from 43 AIS patients with anterior circulation occlusion after thrombectomy and 37 healthy controls (HCs). Both static and dynamic functional connectivity (FC) within four advanced functional networks including dorsal attention network (DAN), ventral attention network (VAN), executive control network (ECN) and default mode network (DMN), were calculated and compared between post-thrombectomy patients and HCs, and between two subgroups of post-thrombectomy patients with different reperfusion conditions. RESULTS: As compared to HCs, patients showed significant differences in static FC of four functional networks, and in dynamic FC of DAN, ECN and DMN. Furthermore, patients with better reperfusion conditions exhibited increased static FC with precuneus, and altered dynamic FC within precuneus. Moreover, these alterations were associated with clinical assessments of stroke severity and functional recovery in post-thrombectomy patients. CONCLUSIONS: Collectively, these findings may provide the potential imaging markers for assessment of thrombectomy efficacy and help establish the specific rehabilitation treatments for post-thrombectomy patients.

Details DOI

ICRA Conference 2021 Conference Paper

Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp

  • Junfan Lin
  • Zhongzhan Huang
  • Keze Wang
  • Xiaodan Liang
  • Weiwei Chen
  • Liang Lin

Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it’s still challenging to apply it to real-world tasks, due to the poor sample efficiency. Attempting to overcome this shortcoming, several works focus on reusing the collected trajectory data during the training by decomposing them into a set of policy-irrelevant discrete transitions. However, their improvements are somewhat marginal since i) the amount of the transitions is usually small, and ii) the value assignment only happens in the joint states. To address these issues, this paper introduces a concise yet powerful method to construct Continuous Transition, which exploits the trajectory information by exploiting the potential transitions along the trajectory. Specifically, we propose to synthesize new transitions for training by linearly interpolating the consecutive transitions. To keep the constructed transitions authentic, we also develop a discriminator to guide the construction process automatically. Extensive experiments demonstrate that our proposed method achieves a significant improvement in sample efficiency on various complex continuous robotic control problems in MuJoCo and outperforms the advanced model-based / model-free RL methods. The source code is available 1.

Details

AIJ Journal 2019 Journal Article

Preservation of semantic properties in collective argumentation: The case of aggregating abstract argumentation frameworks

  • Weiwei Chen
  • Ulle Endriss

An abstract argumentation framework can be used to model the argumentative stance of an agent at a high level of abstraction, by indicating for every pair of arguments that is being considered in a debate whether the first attacks the second. When modelling a group of agents engaged in such a debate, we may wish to aggregate their individual argumentation frameworks to obtain a single such framework that reflects the consensus of the group. While agents typically will not agree on every single attack, there may well be high-level agreement on semantic properties, such as whether a given argument should be accepted or whether there are any acceptable arguments at all. Using techniques from social choice theory, we analyse the circumstances under which such semantic properties agreed upon by the individual agents will be preserved under aggregation. Our results cover semantic properties formulated in terms of six of the most widely used extension-based semantics for abstract argumentation and range from positive results that show that certain aggregation rules can provide the desired preservation guarantees to impossibility theorems that show that certain combinations of requirements cannot be met by any reasonable aggregation rule.

Details DOI