Author name cluster

Junlin Li

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.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Collaboratively “Copy & Paste” 2D-3D Features for Complex Video-to-Video Motion Editing

Jia-Xing Zhong
Shijie Zhao
Junlin Li
Li Zhang

Video-to-video human motion editing aims to transfer motion from a driving video to a reference video while preserving the background dynamics and the protagonist's original appearance. We identify critical limitations in existing methods that fail to capture the full complexity of human motions, particularly regarding: 1) location changes, 2) orientation variations, and 3) complicated non-upright poses. To address these challenges, we propose a framework that collaboratively "copies and pastes" 2D and 3D features across spatio-temporal dimensions into a shared representation space for motion guidance. Our approach achieves this through: 1) a mutual distillation mechanism that enhances the robustness and capability of individual encoders, and 2) a selective fusion module that adaptively weights and combines complementary information from spatio-temporal representations. To evaluate motion editing algorithms under challenging scenarios, we introduce a comprehensive benchmark dataset comprising real-world video clips from artistic gymnastics and figure skating competitions. These sports disciplines naturally encompass the three aforementioned aspects of motion complexity. Extensive experiments demonstrate that our approach significantly outperforms existing methods, particularly in handling intricate human motions.

PDF Details DOI

EAAI Journal 2026 Journal Article

Learnable Daubechies wavelet neural layers: A novel fault diagnosis architecture for high-speed train under severe noise condition

Junxiao Ren
Xuefeng Gao
Qiang Li
Junlin Li

Complex and pervasive noise interference significantly undermines the performance of existing fault diagnosis techniques on high-speed train bogies during operation. Existing methods exhibit pronounced limitations in high-noise environments, demonstrating inadequate adaptability to domain-specific vibrational patterns and a lack of interpretability in their decision-making processes. To address these challenges, this study proposes a novel fault diagnosis architecture that integrates a learnable, parameterized wavelet transform with deep learning. The architecture introduces a Daubechies wavelet neural layer with trainable parameters — scale, translation, and flip — to enable adaptive modulation of the wavelet kernels. Building on this foundation, the architecture incorporates an efficient channel attention mechanism to construct a deep neural structure tailored for fault diagnosis in high-speed train bogies. Experimental results demonstrate that the proposed method achieves an accuracy of 99. 97% across 31 fault categories, substantially outperforming seven state-of-the-art approaches, including transformer-based and attention-based architectures. Robustness evaluations under severe noise conditions show that the model consistently maintains superior diagnostic performance within the range of −10 decibel to 10 decibel. Further validation on real-world Harbin Institute of Technology bearing measurements confirms the method’s reliability under actual operational conditions. The explicit mathematical formulation of Daubechies wavelets provides enhanced model transparency and interpretability, affirming the method’s effectiveness and practical applicability for safety-critical railway condition monitoring systems in real-world operational environments.

Details DOI

AAAI Conference 2026 Conference Paper

Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset

Qifan Liang
Junlin Li
Zhen Han
Xihao Wang
Zhongyuan Wang
Bin Mei

Electrocautery or lasers will inevitably generate surgical smoke, which hinders the visual guidance of laparoscopic videos for surgical procedures. The surgical smoke can be classified into different types based on its motion patterns, leading to distinctive spatio-temporal characteristics across smoky laparoscopic videos. However, existing desmoking methods fail to account for such smoke-type-specific distinctions. Therefore, we propose the first Smoke-Type-Aware Laparoscopic Video Desmoking Network (STANet) by introducing two smoke types: Diffusion Smoke and Ambient Smoke. Specifically, a smoke mask segmentation sub-network is designed to jointly conduct smoke mask and smoke type predictions based on the attention-weighted mask aggregation, while a smokeless video reconstruction sub-network is proposed to perform specially desmoking on smoky features guided by two types of smoke mask. To address the entanglement challenges of two smoke types, we further embed a coarse-to-fine disentanglement module into the mask segmentation sub-network, which yields more accurate disentangled masks through the smoke-type-aware cross attention between non-entangled and entangled regions. In addition, we also construct the first large-scale synthetic video desmoking dataset with smoke type annotations. Extensive experiments demonstrate that our method not only outperforms state-of-the-art approaches in quality evaluations, but also exhibits superior generalization across multiple downstream surgical tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning

Xuanyu Zhang
Weiqi Li
Shijie Zhao
Junlin Li
Li Zhang
Jian Zhang

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited generalization, lack of temporal awareness, heavy reliance on large-scale annotated datasets, and the lack of effective interaction with generation models. Most current approaches rely on supervised fine-tuning of vision-language models (VLMs), which often require large-scale annotated datasets and tend to decouple understanding and generation. To address these shortcomings, we propose VQ-Insight, a novel reasoning-style VLM framework for AIGC video quality assessment. Our approach features: (1) a progressive video quality learning scheme that combines image quality warm-up, general task-specific temporal learning, and joint optimization with the video generation model; (2) the design of multi-dimension scoring rewards, preference comparison rewards, and temporal modeling rewards to enhance both generalization and specialization in video quality evaluation. Extensive experiments demonstrate that VQ-Insight consistently outperforms state-of-the-art baselines in preference comparison, multi-dimension scoring, and natural video scoring, bringing significant improvements for video generation tasks.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Cross-Modality Disentanglement and Fusion via Hyperedge-Centric Graph Learning for Brain Network Connectivity Analysis

Manman Yuan
Jiapei Li
Junlin Li
Jiacheng Wang
Ting Xu
Can Yin

Analyzing brain network connectivity (BNC) using multimodal neuroimaging to identify neurodegenerative diseases has attracted increasing attention. However, current methods largely rely on node-centric graphs and assume structural or semantic alignment across modalities, limiting the capture of high-order interactions and modality-specific patterns critical for accurate disease identification. In this paper, we propose a novel Hyperedge-Centric Graph Learning Network (HCGLNet) to address these limitations. Specifically, we present a hyperedge-centric graph construction strategy (HGC) that represents each modality as a hyperedge-centric graph, explicitly modelling high-order connectivity unique to each modality. Moreover, we design a disentangled latent learning module (DLM) that factorize shared and specific representations, preserving modality-specific features from dilution while enabling the extraction of shared cross-modal representations. Finally, we develop a representation-aware routing (RAR) algorithm to adaptively fuse modality-specific and shared features based on learned weights, enhancing discriminability for downstream tasks. Experiments on three real-world datasets show that our HCGLNet abstraction reduces graph size by over 80%, lowers computation, and achieves state-of-the-art performance in neurodegenerative disease classification.

Details

ECAI Conference 2025 Conference Paper

D-HyperNet: Brain Disorder Identification in Directed Hypergraph via Effective Network Construction and Flow-Aware Feature Aggregation

Manman Yuan
Weiming Jia
Jiejie Fan
Junlin Li
Jiazhen Ye
Can Yin

Hypergraphs provide excellent modeling ability for brain disorder identification, especially in capturing high-order interactions among regions of interest (ROIs). Nevertheless, existing methods overlook the impact of directional hyperedges learning on the brain network, leading to wasteful functional connectivity and poor identification performance. To address the above issue, this paper proposes a novel Brain Disorder Identification method via Directed Hypergraph Networks (D-HyperNet). Specifically, our methodology employs an Effective Network Construction module to capture causal dependencies and infer directional functional connectivity among ROIs. Followed by the Flow-aware Feature Aggregation module, which designs a novel directed hypergraph encoder that directionally aggregates node features, effectively improving the accuracy and reliability of brain network representations. Additionally, we are integrating the proposed encoder into a contrastive learning program to obtain a more robust whole-brain representation. Extensive experiments demonstrate the efficacy of our D-HyperNet approach. The code is available at https: //github. com/Jia-Weiming/D-HyperNet.

Details

IROS Conference 2025 Conference Paper

FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion

Yansong Xu
Junlin Li
Wei Zhang 0071
Siyu Chen
Shengyong Zhang
Yuquan Leng
Weijia Zhou

3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling realtime positioning and the construction of high-fidelity maps. However, the uncertainty in gaussian position and initialization parameters introduces challenges, often requiring extensive iterative convergence and resulting in redundant or insufficient gaussian representations. To address this, we introduce a novel adaptive densification method based on Fourier frequency domain analysis to establish gaussian priors for rapid convergence. Additionally, we propose constructing independent and unified sparse and dense maps, where a sparse map supports efficient tracking via Generalized Iterative Closest Point (GICP) and a dense map creates high-fidelity visual representations. This is the first SLAM system leveraging frequency domain analysis to achieve high-quality gaussian mapping in realtime. Experimental results demonstrate an average frame rate of 36 FPS on Replica and TUM RGB-D datasets, achieving competitive accuracy in both localization and mapping. The source code is publicly available at https://github.com/3DV-Coder/FGS-SLAM.

Details

ICML Conference 2025 Conference Paper

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

Yaoyang Liu
Junlin Li
Yinjun Wu
Zhen Chen

Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages one LLM for query decomposition and searches the optimal prompt with an LLM-based optimizer. We further propose an end-to-end training algorithm to alternatively optimize the prompt for query decomposition and the downstream models. This algorithm can achieve superior MVR performance at a reasonable training cost as our theoretical analysis suggests. POQD can be integrated seamlessly into arbitrary retrieval-based systems such as Retrieval-Augmented Generation (RAG) systems. Extensive empirical studies on representative RAG-based QA tasks show that POQD outperforms existing query decomposition strategies in both retrieval performance and end-to-end QA accuracy. POQD is available at https: //github. com/PKU-SDS-lab/POQD-ICML25.

Details

NeurIPS Conference 2025 Conference Paper

Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

Weiqi Li
Xuanyu Zhang
Shijie Zhao
Yabin ZHANG
Junlin Li
Li Zhang
Jian Zhang

Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language models (MLLMs) has significantly broadened the scope of IQA, moving toward comprehensive image quality understanding that incorporates content analysis, degradation perception, and comparison reasoning beyond mere numerical scoring. Previous MLLM-based methods typically either generate numerical scores lacking interpretability or heavily rely on supervised fine-tuning (SFT) using large-scale annotated datasets to provide descriptive assessments, limiting their flexibility and applicability. In this paper, we propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO), which demonstrates strong visual reasoning capability for image quality understanding while requiring only a limited amount of rating scores and degradation labels. By jointly optimizing score regression and degradation perception tasks with carefully designed reward functions, our approach effectively exploits their mutual benefits for enhanced performance. Extensive experiments demonstrate that Q-Insight substantially outperforms existing state-of-the-art methods on both score regression and degradation perception tasks, while exhibiting impressive zero-shot generalization and superior comparison reasoning capability. The code and models are available at https: //github. com/bytedance/Q-Insight.

PDF Details

EAAI Journal 2024 Journal Article

A hierarchical integration scheduling method for flexible job shop with green lot splitting

Qingshan Gong
Junlin Li
Zhigang Jiang
Yan Wang

The integration of green scheduling and lot splitting scheduling is indispensable for ensuring the coordinated optimization of economic and environmental benefits in flexible job-shop scheduling (FJS). However, this integration involves not only the indicator of greenness and economy but also the process of production planning and scheduling, which is substantially complicated. To this end, a hierarchical integrated scheduling method is proposed by comprehensively considering the multilevel organizational structure and task configuration characteristics of flexible job-shop, as well as the differences in objectives on different scheduling levels: workshop level, process unit level, machine tool level. On the workshop level, a lot splitting model is presented to obtain the optimal processing task set for each production cycle with the minimum expected cost (startup cost, tardiness cost, and holding cost). On the process unit level, a task allocation model is given to allocate the optimal workload for each machine tool with the minimum processing energy consumption and maximum machine load. On the machine tool level, an operation sequencing model is established to obtain the optimal processing sequence for each machine tool with the minimum standby energy consumption and makespan. According to the solving characteristics of the hierarchical models, a multi-objective algorithm is applied. Finally, a case study is demonstrated to validate the proposed method.

Details DOI

ICML Conference 2024 Conference Paper

An Iterative Min-Min Optimization Method for Sparse Bayesian Learning

Yasen Wang
Junlin Li
Zuogong Yue
Ye Yuan 0002

As a well-known machine learning algorithm, sparse Bayesian learning (SBL) can find sparse representations in linearly probabilistic models by imposing a sparsity-promoting prior on model coefficients. However, classical SBL algorithms lack the essential theoretical guarantees of global convergence. To address this issue, we propose an iterative Min-Min optimization method to solve the marginal likelihood function (MLF) of SBL based on the concave-convex procedure. The method can optimize the hyperparameters related to both the prior and noise level analytically at each iteration by re-expressing MLF using auxiliary functions. Particularly, we demonstrate that the method globally converges to a local minimum or saddle point of MLF. With rigorous theoretical guarantees, the proposed novel SBL algorithm outperforms classical ones in finding sparse representations on simulation and real-world examples, ranging from sparse signal recovery to system identification and kernel regression.

Details

IJCAI Conference 2024 Conference Paper

CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment

Kanglei Zhou
Junlin Li
Ruizhi Cai
Liyuan Wang
Xingxing Zhang
Xiaohui Liang

Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA datasets. However, this common strategy yields suboptimal results due to the inherent struggle of these backbones to capture the subtle cues essential for AQA. Moreover, fine-tuning on smaller datasets risks overfitting. To address these issues, we propose Coarse-to-Fine Instruction Alignment (CoFInAl). Inspired by recent advances in large language model tuning, CoFInAl aligns AQA with broader pre-trained tasks by reformulating it as a coarse-to-fine classification task. Initially, it learns grade prototypes for coarse assessment and then utilizes fixed sub-grade prototypes for fine-grained assessment. This hierarchical approach mirrors the judging process, enhancing interpretability within the AQA framework. Experimental results on two long-term AQA datasets demonstrate CoFInAl achieves state-of-the-art performance with significant correlation gains of 5. 49% and 3. 55% on Rhythmic Gymnastics and Fis-V, respectively. Our Code is available at https: //github. com/ZhouKanglei/CoFInAl_AQA.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Panoramic Video Salient Object Detection with Ambisonic Audio Guidance

Xiang Li
Haoyuan Cao
Shijie Zhao
Junlin Li
Li Zhang
Bhiksha Raj

Video salient object detection (VSOD), as a fundamental computer vision problem, has been extensively discussed in the last decade. However, all existing works focus on addressing the VSOD problem in 2D scenarios. With the rapid development of VR devices, panoramic videos have been a promising alternative to 2D videos to provide immersive feelings of the real world. In this paper, we aim to tackle the video salient object detection problem for panoramic videos, with their corresponding ambisonic audios. A multimodal fusion module equipped with two pseudo-siamese audio-visual context fusion (ACF) blocks is proposed to effectively conduct audio-visual interaction. The ACF block equipped with spherical positional encoding enables the fusion in the 3D context to capture the spatial correspondence between pixels and sound sources from the equirectangular frames and ambisonic audios. Experimental results verify the effectiveness of our proposed components and demonstrate that our method achieves state-of-the-art performance on the ASOD60K dataset.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

Jinhai Yang
Mengxi Guo
Shijie Zhao
Junlin Li
Li Zhang

High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-to-end asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP). Code is available at https://github.com/yang-jin-hai/SAIN.

PDF Details DOI