Author name cluster

Jie Liang

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.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

Pano-GS: Perception-Aware Gaussian Optimization with Gradient Consistency and Multi-Criteria Densification for High-Quality Rendering

Yang Deng
Zhanke Wang
Jiahao Wu
Jie Liang
Jingui Ma
Yang Hu
Ronggang Wang

Reconstructing 3D scenes from multi-view image sequences remains a significant challenge in practical applications. While recent advances in 3D Gaussian Splatting have enabled high-quality rendering, existing methods rely heavily on pixel-level L1 loss, which misaligns with human perception, leading to a lack of high-frequency details and the emergence of artifacts. Additionally, the position gradient-based densification strategy often results in under-densified Gaussian primitives, thereby degrading rendering quality. To address these challenges, we propose Pano-GS, a perception-aware Gaussian optimization framework. Specifically, we introduce a gradient consistency-constrained loss to capture high-frequency details, mitigating the inherent shortcomings of traditional L1 loss and enhancing reconstruction fidelity. In addition, we use a multi-criteria densification strategy to reduce the sole reliance on average position gradients. Extensive experiments demonstrate that Pano-GS achieves state-of-the-art performance, confirming its effectiveness and robust generalization across diverse real-world scenes.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes

Lishen Qu
Zhihao Liu
Shihao Zhou
LUO YAQI
Jie Liang
Hui Zeng
Lei Zhang
Jufeng Yang

Flicker artifacts in short-exposure images are caused by the interplay between the row-wise exposure mechanism of rolling shutter cameras and the temporal intensity variations of alternating current (AC)-powered lighting. These artifacts typically appear as uneven brightness distribution across the image, forming noticeable dark bands. Beyond compromising image quality, this structured noise also affects high-level tasks, such as object detection and tracking, where reliable lighting is crucial. Despite the prevalence of flicker, the lack of a large-scale, realistic dataset has been a significant barrier to advancing research in flicker removal. To address this issue, we present BurstDeflicker, a scalable benchmark constructed using three complementary data acquisition strategies. First, we develop a Retinex-based synthesis pipeline that redefines the goal of flicker removal and enables controllable manipulation of key flicker-related attributes (e. g. , intensity, area, and frequency), thereby facilitating the generation of diverse flicker patterns. Second, we capture 4, 000 real-world flicker images from different scenes, which help the model better understand the spatial and temporal characteristics of real flicker artifacts and generalize more effectively to wild scenarios. Finally, due to the non-repeatable nature of dynamic scenes, we propose a green-screen method to incorporate motion into image pairs while preserving real flicker degradation. Comprehensive experiments demonstrate the effectiveness of our dataset and its potential to advance research in flicker removal.

PDF Details

NeurIPS Conference 2025 Conference Paper

VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank

Tianhe Wu
Jian Zou
Jie Liang
Lei Zhang
Kede Ma

DeepSeek-R1 has demonstrated remarkable effectiveness in incentivizing reasoning and generalization capabilities of large language models (LLMs) through reinforcement learning. Nevertheless, the potential of reasoning-induced computation has not been thoroughly explored in the context of image quality assessment (IQA), a task depending critically on visual reasoning. In this paper, we introduce VisualQuality-R1, a reasoning-induced no-reference IQA (NR-IQA) model, and we train it with reinforcement learning to rank, a learning algorithm tailored to the intrinsically relative nature of visual quality. Specifically, for a pair of images, we employ group relative policy optimization to generate multiple quality scores for each image. These estimates are used to compute comparative probabilities of one image having higher quality than the other under the Thurstone model. Rewards for each quality estimate are defined using continuous fidelity measures rather than discretized binary labels. Extensive experiments show that the proposed VisualQuality-R1 consistently outperforms discriminative deep learning-based NR-IQA models as well as a recent reasoning-induced quality regression method. Moreover, VisualQuality-R1 is capable of generating contextually rich, human-aligned quality descriptions, and supports multi-dataset training without requiring perceptual scale realignment. These features make VisualQuality-R1 especially well-suited for reliably measuring progress in a wide range of image processing tasks like super-resolution and image generation.

PDF Details

AAAI Conference 2023 Conference Paper

Learning Conflict-Noticed Architecture for Multi-Task Learning

Zhixiong Yue
Yu Zhang
Jie Liang

Multi-task learning has been widely used in many applications to enable more efficient learning by sharing part of the architecture across multiple tasks. However, a major challenge is the gradient conflict when optimizing the shared parameters, where the gradients of different tasks could have opposite directions. Directly averaging those gradients will impair the performance of some tasks and cause negative transfer. Different from most existing works that manipulate gradients to mitigate the gradient conflict, in this paper, we address this problem from the perspective of architecture learning and propose a Conflict-Noticed Architecture Learning (CoNAL) method to alleviate the gradient conflict by learning architectures. By introducing purely-specific modules specific to each task in the search space, the CoNAL method can automatically learn when to switch to purely-specific modules in the tree-structured network architectures when the gradient conflict occurs. To handle multi-task problems with a large number of tasks, we propose a progressive extension of the CoNAL method. Extensive experiments on computer vision, natural language processing, and reinforcement learning benchmarks demonstrate the effectiveness of the proposed methods.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Learned Bi-Resolution Image Coding using Generalized Octave Convolutions

Mohammad Akbari
Jie Liang
Jingning Han
Chengjie Tu

Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art ratedistortion (R-D) performance has been achieved by contextadaptive entropy coding approaches in which hyperprior and autoregressive models are jointly utilized to effectively capture the spatial dependencies in the latent representations. However, the latents are feature maps of the same spatial resolution in previous works, which contain some redundancies that affect the R-D performance. In this paper, we propose a learned bi-resolution image coding approach that is based on the recently developed octave convolutions to factorize the latents into high and low resolution components. Therefore, the spatial redundancy is reduced, which improves the R-D performance. Novel generalized octave convolution and octave transposed-convolution architectures with internal activation layers are also proposed to preserve more spatial structure of the information. Experimental results show that the proposed scheme outperforms all existing learned methods as well as standard codecs such as the next-generation video coding standard VVC (4: 2: 0) in both PSNR and MS-SSIM. We also show that the proposed generalized octave convolution can improve the performance of other auto-encoder-based schemes such as semantic segmentation and image denoising.

PDF Details

JBHI Journal 2019 Journal Article

Guest Editorial on the Special Issue on Integrating Informatics and Technology for Precision Medicine

Constantinos S. Pattichis
Constantinos Pitris
Jie Liang
Yuanting Zhang

The seven papers in this special section examine the latest advances in the field of integrated precision medicine technologies. In the majority of medical conditions common therapeutic approaches are usually effective in only a small percentage of the patient population. Recent scientific discoveries implicate as possible causes of this lack of effect the multifactorial nature of most diseases and the patient variability in disease expression, genetic disposition, and environmental exposures. It has become apparent that in order to improve the response to therapy and long term prognosis, treatment must be specifically tailored to the disease and the patient. Precision medicine is an attempt to maximize effectiveness by taking into account individual variability in clinical presentation, medical history, genes, environment, and lifestyle. It is a leap beyond the promise of “personalization” empowered by recent technological advances. However, progress in precision medicine has been slow due to the lack of “precision” in the traditional research, translation, and clinical practice. Current approaches are largely empirical, fragmented, lack integration, and rely on population statistics, with inadequate feedback between disciplines. In addition, most of the information required for personalization is either missing or unutilized. New technological developments can help overcome these hurdles of imprecision to achieve the full promise of precision medicine.

Details DOI

AAAI Conference 2018 Conference Paper

Automatic Model Selection in Subspace Clustering via Triplet Relationships

Jufeng Yang
Jie Liang
Kai Wang
Yong-Liang Yang
Ming-Ming Cheng

This paper addresses both the model selection (i. e. estimating the number of clusters K) and subspace clustering problems in a uniﬁed model. The real data always distribute on a union of low-dimensional sub-manifolds which are embedded in a high-dimensional ambient space. In this regard, the state-ofthe-art subspace clustering approaches ﬁrstly learn the afﬁnity among samples, followed by a spectral clustering to generate the segmentation. However, arguably, the intrinsic geometrical structures among samples are rarely considered in the optimization process. In this paper, we propose to simultaneously estimate K and segment the samples according to the local similarity relationships derived from the afﬁnity matrix. Given the correlations among samples, we deﬁne a novel data structure termed the Triplet, each of which reﬂects a high relevance and locality among three samples which are aimed to be segmented into the same subspace. While the traditional pairwise distance can be close between inter-cluster samples lying on the intersection of two subspaces, the wrong assignments can be avoided by the hyper-correlation derived from the proposed triplets due to the complementarity of multiple constraints. Sequentially, we propose to greedily optimize a new model selection reward to estimate K according to the correlations between inter-cluster triplets. We simultaneously optimize a fusion reward based on the similarities between triplets and clusters to generate the ﬁnal segmentation. Extensive experiments on the benchmark datasets demonstrate the effectiveness and robustness of the proposed approach.

PDF Details

TIST Journal 2018 Journal Article

D-Map+

Siming Chen
Shuai Chen
Zhenhuang Wang
Jie Liang
Yadong Wu
Xiaoru Yuan

Information diffusion analysis is important in social media. In this work, we present a coherent ego-centric and event-centric model to investigate diffusion patterns and user behaviors. Applying the model, we propose Diffusion Map+ (D-Maps+), a novel visualization method to support exploration and analysis of user behaviors and diffusion patterns through a map metaphor. For ego-centric analysis, users who participated in reposting (i.e., resending a message initially posted by others) one central user’s posts (i.e., a series of original tweets) are collected. Event-centric analysis focuses on multiple central users discussing a specific event, with all the people participating and reposting messages about it. Social media users are mapped to a hexagonal grid based on their behavior similarities and in the chronological order of repostings. With the additional interactions and linkings, D-Map+ is capable of providing visual profiling of influential users, describing their social behaviors and analyzing the evolution of significant events in social media. A comprehensive visual analysis system is developed to support interactive exploration with D-Map+. We evaluate our work with real-world social media data and find interesting patterns among users and events. We also perform evaluations including user studies and expert feedback to certify the capabilities of our method.

Details DOI

AAAI Conference 2018 Conference Paper

Understanding Image Impressiveness Inspired by Instantaneous Human Perceptual Cues

Jufeng Yang
Yan Sun
Jie Liang
Yong-Liang Yang
Ming-Ming Cheng

With the explosion of visual information nowadays, millions of digital images are available to the users. How to efﬁciently explore a large set of images and retrieve useful information thus becomes extremely important. Unfortunately only some of the images can impress the user at ﬁrst glance. Others that make little sense in human perception are often discarded, while still costing valuable time and space. Therefore, it is signiﬁcant to identify these two kinds of images for relieving the load of online repositories and accelerating information retrieval process. However, most of the existing image properties, e. g. , memorability and popularity, are based on repeated human interactions, which limit the research and application of evaluating image quality in terms of instantaneous impression. In this paper, we propose a novel image property, called impressiveness, that measures how images impress people with a short-term contact. This is based on an impression-driven model inspired by a number of important human perceptual cues. To achieve this, we ﬁrst collect three datasets in various domains, which are labeled according to the instantaneous sensation of the annotators. Then we investigate the impressiveness property via six established human perceptual cues as well as the corresponding features from pixel to semantic levels. Sequentially, we verify the consistency of the impressiveness which can be quantitatively measured by multiple visual representations, and evaluate their latent relationships. Finally, we apply the proposed impressiveness property to rank the images for an efﬁcient image recommendation system.

PDF Details

JBHI Journal 2015 Journal Article

Guest Editorial EMBC 2014

Walter Besio
Leslie Ying
Jie Liang
Nigel Lovell
Carmen C.Y. Poon
May D. Wang

The ten papers from this special sectoin were presented at the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’14).

Details DOI

EAAI Journal 2007 Journal Article

Modeling research on the sorption kinetics of pentachlorophenol (PCP) to sediments based on neural networks and neuro-fuzzy systems

Xiao-kang Su
Guang-ming Zeng
Guo-he Huang
Jian-bing Li
Jie Liang
Ling-ling Wang
Chun-yan Du

The sorption kinetics of pentachlorophenol (PCP) to sediments (from 8 different lakes, south of China) was studied in batch experiments. The comparison of a radial basis function neural network (RBFN) and an adaptive neuro-fuzzy inference system (ANFIS) applied for modeling the sorption behaviors was presented. Although the physical and chemical characteristics were different, the modeling results showed that the sorption behaviors of 8 different sediments were similar. Both RBFN and ANFIS could model the sorption behaviors and make predictions in high accuracy, which illustrated that the two models reflected the internal principle of the sorption better than the traditional model Fick's second law (FSL). Especially, RBFN held the promise of being able to work under noisy conditions to obtain high accuracy. In conclusion, RBFN was the valid options for modeling the sorption kinetics of PCP to the lake sediments. The individual changes of the three different inputs (the concentration of PCP in the aqueous phase, the reversible fraction and the irreversible fraction) affected the modeling results to the similar extent, from which we could infer that the sorption kinetics of PCP to these sediments were affected by all the three factors rather than only by the concentration of PCP in the aqueous phase.

Details DOI