Author name cluster

Yutao Liu

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

1 author row

AAAI Conference 2026 Conference Paper

FVNet: Harnessing Liquid Neural Dynamics for Lightweight Visual Representation

Zhenzhe Hou
Xiaohui Chu
Runze Hu
Yang Li
Yutao Liu

Efficient visual backbone design remains crucial for resource-constrained computer vision applications. Inspired by the adaptive continuous-time dynamics observed in biological neurons, we propose FVNet, a novel lightweight architecture that integrates liquid neural dynamics for efficient and dynamic visual feature extraction. Central to FVNet is the Fluid Temporal Flow Unit (FTFU), which employs continuous-time equations with learnable time constants to capture spatio-temporal dependencies adaptively. By further stacking these units in a Multi-Phase Fluid Block (MPFB), our model processes features across parallel temporal scales, enabling context-aware feature encoding without incurring excessive computational overhead. Through a discrete closed-form solution, FVNet achieves the representational power of continuous-time models while avoiding the instability and overhead of iterative numerical solvers. Extensive experiments on various vision tasks demonstrate that FVNet achieves superior performance and efficiency over existing state-of-the-art lightweight networks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment

Jingchao Cao
Guo An
Feng Gao
Ke Gu
Yutao Liu

Despite the rapid progress of multimodal large language models (MLLMs), their capacity for low-level visual perception in underwater environments remains underexplored. To address this gap, we present UQ-Bench, the first systematically designed benchmark for evaluating the ability of MLLMs to perceive and assess underwater image quality at the low-level visual attribute level. UQ-Bench comprises three components: (1) UW-Perception, a dataset of 3,000 underwater images paired with targeted questions on key degradations such as color cast, blur, contrast, and exposure, covering both global and local perceptual dimensions; (2) UW-Describe, a dataset of 500 images with expert-annotated gold-standard descriptions for assessing the accuracy of model-generated text; and (3) UW-Eval, an evaluation protocol employing human mean opinion scores (MOS) for quantitative quality assessment. To ensure rigorous and reproducible benchmarking, we propose a GPT-assisted evaluation framework that aligns model outputs with expert references and enables fine-grained analysis of distortion perception. Experimental results demonstrate that while MLLMs exhibit preliminary competence in underwater low-level visual tasks, they still fall short in capturing subtle degradations and achieving human-level consistency, highlighting the need for further advances in foundation models for marine vision.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning

Wensheng Pan
Timin Gao
Yan Zhang
Xiawu Zheng
Yunhang Shen
Ke Li
Runze Hu
Yutao Liu

Blind Image Quality Assessment (BIQA) aims to simulate human assessment of image quality. It has a great demand for labeled data, which is often insufficient in practice. Some researchers employ unsupervised methods to address this issue, which is challenging to emulate the human subjective system. To this end, we introduce a unified framework that combines semi-supervised and incremental learning to address the mentioned issue. Specifically, when training data is limited, semi-supervised learning is necessary to infer extensive unlabeled data. To facilitate semi-supervised learning, we use knowledge distillation to assign pseudo-labels to unlabeled data, preserving analytical capability. To gradually improve the quality of pseudo labels, we introduce incremental learning. However, incremental learning can lead to catastrophic forgetting. We employ Experience Replay by selecting representative samples during multiple rounds of semi-supervised learning, to alleviate forgetting and ensure model stability. Experimental results show that the proposed approach achieves state-of-the-art performance across various benchmark datasets. After being trained on the LIVE dataset, our method can be directly transferred to the CSIQ dataset. Compared with other methods, it significantly outperforms unsupervised methods on the CSIQ dataset with a marginal performance drop (-0.002) on the LIVE dataset. In conclusion, our proposed method demonstrates its potential to tackle the challenges in real-world production processes.

PDF Details DOI

EAAI Journal 2023 Journal Article

A novel shape-based averaging algorithm for time series

Yutao Liu
Yong-An Zhang
Ming Zeng
Jie Zhao

Time series averaging is one of the essential subroutines in time series analysis. DTW Barycenter Averaging (DBA) has proven to be an effective and popular DTW-based time series averaging algorithm. However, DBA lacks the ability to average time series in the time domain, making it sensitive to initialization. In this research, we propose a novel shape-based time series averaging algorithm, called Shape DTW Weighted Averaging (ShapeDWA), to address the shortcomings of DBA. The proposed ShapeDWA algorithm combines the advantages of the DBA and the Cubic-spline DTW (CDTW) averaging methods. The concepts of time index averaging and re-sampling in the CDTW algorithm are incorporated into the DBA algorithm, giving ShapeDWA the ability to average a set of time series in both the amplitude and time domains. Moreover, ShapeDWA utilizes a weighed average instead of the barycenter average in DBA, which effectively attenuate the effects of noise, outliers, and local amplitude differences between the time series. To qualitatively evaluate and compare the proposed time series averaging algorithm, two metrics have been developed: average discrepancy distance and average time distortion. Extensive experimental results on the UCR time series database illustrate the superior performance of ShapeDWA over DBA and SSG, with an average reduction of 23. 42% and 24. 89% for average discrepancy distance, and 18. 76% and 19. 81% for average time distortion. Furthermore, the template matching-based classification experiment shows that ShapeDWA combined with these two developed metrics improves the classification rate by 17. 07% and 16. 42% compared to DBA and SSG, respectively.

Details DOI

AAAI Conference 2023 Conference Paper

Data-Efficient Image Quality Assessment with Attention-Panel Decoder

Guanyi Qin
Runze Hu
Yutao Liu
Xiawu Zheng
Haotian Liu
Xiu Li
Yan Zhang

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a novel BIQA pipeline based on the Transformer architecture, which achieves an efficient quality-aware feature representation with much fewer data. More specifically, we consider the traditional fine-tuning in BIQA as an interpretation of the pre-trained model. In this way, we further introduce a Transformer decoder to refine the perceptual information of the CLS token from different perspectives. This enables our model to establish the quality-aware feature manifold efficiently while attaining a strong generalization capability. Meanwhile, inspired by the subjective evaluation behaviors of human, we introduce a novel attention panel mechanism, which improves the model performance and reduces the prediction uncertainty simultaneously. The proposed BIQA method maintains a light-weight design with only one layer of the decoder, yet extensive experiments on eight standard BIQA datasets (both synthetic and authentic) demonstrate its superior performance to the state-of-the-art BIQA methods, i.e., achieving the SRCC values of 0.875 (vs. 0.859 in LIVEC) and 0.980 (vs. 0.969 in LIVE). Checkpoints, logs and code will be available at https://github.com/narthchin/DEIQT.

PDF Details DOI