Author name cluster

Hefei Ling

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.

13 papers

2 author rows

AAAI Conference 2026 Conference Paper

Dual-stream Relation-modeling Disentanglement for Cloth-Changing Person Re-Identification

Shijuan Huang
Hefei Ling
Zongyi Li
Xu Li
Zhao Lv

Cloth-changing person re-identification (CC-ReID) aims to identify individuals across non-overlapping cameras despite clothing variations. Existing methods are often constrained by two primary limitations: approaches using auxiliary modalities typically rely on a single specific cue, limiting their robustness, while feature disentanglement methods struggle with discrete labels that create inconsistencies between ground truth labels and modality semantic similarity. To overcome these limitations, we propose DRDnet, a unified framework that synergistically integrates dual auxiliary cues and advanced relation modeling. Specifically, our Dual-Stream Disentanglement (DSD) module leverages textual descriptions and parsing images to decouple clothing factors through high-level semantic supervision and pixel-level operations, yielding robust clothing-agnostic features. Simultaneously, our Modal Relation Modeling (MRM) module constructs feature memory banks and employs adaptive soft label smoothing, effectively enhancing image-text semantic alignment and reinforcing identity consistency across clothing changes. We evaluate DRDnet on several CC-ReID benchmarks to demonstrate its effectiveness and provide state-of-the-art performance across all benchmarks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

GlyphShield: Document Watermarking for the Physical World via Vector Typeface Synthesis

Nan Sun
Yuxing Lu
Han Fang
Hefei Ling
Sijing Xie
LuYu Yuan
Chengxin Zhao

Document protection has become a critical issue for preventing unauthorized copying, distribution, and tampering. Document encryption is a proven solution, but it is not resistant to attacks from the physical world such as screenshots, printing and photographing. A common document protection technique is font-based watermarking, which embeds imperceptible information by using sets of visually similar glyphs to encode traceable data. However, due to the non-differentiable rendering process of vector fonts, these methods often rely on time-consuming and laborious manual design. To address this challenge, we present GlyphShield, an innovative end-to-end vector font watermarking framework. We resolve the non-differentiability challenge by simulating differentiable rasterization through the computation of Signed Distance Field (SDF) for Bézier curves in vector fonts. Besides, to handle complex vector font structures, a novel dual-branch vector encoder is employed to ensure high-quality font synthesis. Extensive experiments demonstrate that our approach ensures more natural and smoother message embedding while ensuring robustness against noise attacks in diverse scenarios. Additionally, our framework demonstrates strong generalization across various font styles and languages.

PDF Details DOI

ICLR Conference 2025 Conference Paper

ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation

Zongyi Li
Shujie Hu
Shujie Liu 0001
Long Zhou
Jeongsoo Choi
Lingwei Meng
Xun Guo
Jinyu Li 0001

Text-to-video (T2V) models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive (\textbf{AR}) models for long (\textbf{LON}) video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model effectively. Specifically, ARLON incorporates several key innovations: 1) A latent Vector Quantized Variational Autoencoder (VQ-VAE) compresses the input latent space of the DiT model into compact and highly quantized visual tokens, bridging the AR and DiT models and balancing the learning complexity and information density; 2) An adaptive norm-based semantic injection module integrates the coarse discrete visual units from the AR model into the DiT model, ensuring effective guidance during video generation; 3) To enhance the tolerance capability of noise introduced from the AR inference, the DiT model is trained with coarser visual latent tokens incorporated with an uncertainty sampling module. Experimental results demonstrate that ARLON significantly outperforms the baseline OpenSora-V1.2 on eight out of eleven metrics selected from VBench, with notable improvements in dynamic degree and aesthetic quality, while delivering competitive results on the remaining three and simultaneously accelerating the generation process. In addition, ARLON achieves state-of-the-art performance in long video generation, outperforming other open-source models in this domain. Detailed analyses of the improvements in inference efficiency are presented, alongside a practical application that demonstrates the generation of long videos using progressive text prompts. Project page: \url{http://aka.ms/arlon}.

Details

NeurIPS Conference 2025 Conference Paper

Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling

Linnan Tu
Lingwei Meng
Zongyi Li
Hefei Ling
Shijuan Huang

Existing efforts in motion synthesis typically utilize either generative transformers with discrete representations or diffusion models with continuous representations. However, the discretization process in generative transformers can introduce motion errors, while the sampling process in diffusion models tends to be slow. In this paper, we propose a novel text-to-motion synthesis method GMMotion that combines a continuous motion representation with an autoregressive model, using the Gaussian mixture model (GMM) to represent the conditional probability distribution. Unlike autoregressive approaches relying on residual vector quantization, our model employs continuous motion representations derived from the VAE's latent space. This choice streamlines both the training and the inference processes. Specifically, we utilize a causal transformer to learn the distributions of continuous motion representations, which are modeled with a learnable Gaussian mixture model. Extensive experiments demonstrate that our model surpasses existing state-of-the-art models in the motion synthesis task.

PDF Details

AAAI Conference 2025 Conference Paper

END^2: Robust Dual-Decoder Watermarking Framework Against Non-Differentiable Distortions

Nan Sun
Han Fang
Yuxing Lu
Chengxin Zhao
Hefei Ling

DNN-based watermarking methods have rapidly advanced, with the ``Encoder-Noise Layer-Decoder'' (END) framework being the most widely used. To ensure end-to-end training, the noise layer in the framework must be differentiable. However, real-world distortions are often non-differentiable, leading to challenges in end-to-end training. Existing solutions only treat the distortion perturbation as additive noise, which does not fully integrate the effect of distortion in training. To better incorporate non-differentiable distortions into training, we propose a novel dual-decoder architecture (END^2). Unlike conventional END architecture, our method employs two structurally identical decoders: the Teacher Decoder, processing pure watermarked images, and the Student Decoder, handling distortion-perturbed images. The gradient is backpropagated only through the Teacher Decoder branch to optimize the encoder thus bypassing the problem of non-differentiability. To ensure resistance to arbitrary distortions, we enforce alignment of the two decoders' feature representations by maximizing the cosine similarity between their intermediate vectors on a hypersphere. Extensive experiments demonstrate that our scheme outperforms state-of-the-art algorithms under various non-differentiable distortions. Moreover, even without the differentiability constraint, our method surpasses baselines with a differentiable noise layer. Our approach is effective and easily implementable across all END architectures, enhancing practicality and generalizability.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Exploring the Potential of Large Vision-Language Models for Unsupervised Text-Based Person Retrieval

Zongyi Li
Li Jianbo
Yuxuan Shi
Jiazhong Chen
Shijuan Huang
Linnan Tu
Fei Shen
Hefei Ling

The aim of text-based person retrieval is to identify pedestrians using natural language descriptions within a large-scale image gallery. Traditional methods rely heavily on manually annotated image-text pairs, which are resource-intensive to obtain. With the emergence of Large Vision-Language Models (LVLMs), the advanced capabilities of contemporary models in image understanding have led to the generation of highly accurate captions. Therefore, this paper explores the potential of employing Large Vision-Language Models for unsupervised text-based pedestrian image retrieval and proposes a Multi-grained Uncertainty Modeling and Alignment framework (MUMA). Initially, multiple Large Vision-Language Models are employed to generate diverse and hierarchically structured pedestrian descriptions across different styles and granularities. However, the generated captions inevitably introduce noise. To address this issue, an uncertainty-guided sample filtration module is proposed to estimate and filter out unreliable image-text pairs. Additionally, to simulate the diversity of styles and granularities in captions, a multi-grained uncertainty modeling approach is applied to model the distributions of captions, with each caption represented as a multivariate Gaussian distribution. Finally, a multi-level consistency distillation loss is employed to integrate and align the multi-grained captions, aiming to transfer knowledge across different granularities. Experimental evaluations conducted on three widely-used datasets demonstrate the significant advancements achieved by our approach.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Multi-Branch Clothes-Agnostic Feature Learning for Cloth-Changing Person Re-Identification

Shijuan Huang
Hefei Ling

Person Re-Identification (Re-ID) is crucial for video surveillance and multi-camera tracking, yet traditional methods struggle with clothing changes that undermine their reliability. This paper introduces a novel multi-branch clothes-agnostic feature learning framework to address cloth-changing person re-identification (CC-ReID), which comprises two key modules: Multi-grained Clothes Caption Generation (MCG), and Multi-Branch Clothes-Agnostic Feature Extraction (MAE). MCG leverages Large Vision-Language Models to generate diverse coarse-to-fine clothing descriptions, reducing the impact of clothing on feature extraction. MAE employs a dual-branch architecture combining Semantic-Guided Feature Extraction (SGE) and Parsing Image Feature Extraction (PIE) to focus on identity-related features while minimizing dependence on clothing characteristics. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance for CC-ReID tasks, showcasing our method’s effectiveness in real-world applications.

Details

NeurIPS Conference 2025 Conference Paper

Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and Scaling

Nan Sun
LuYu Yuan
Han Fang
Yuxing Lu
Hefei Ling
Sijing Xie
Chengxin Zhao

Recent developments in DNN-based image watermarking techniques have achieved impressive results in protecting digital content. However, most existing methods are constrained to low-resolution images as they need to encode the entire image, leading to prohibitive memory and computational costs when applied to high-resolution images. Moreover, they lack robustness to distortions prevalent in large-image transmission, such as extreme scaling and random cropping. To address these issues, we propose a novel watermarking method based on implicit neural representations (INRs). Leveraging the properties of INRs, our method employs resolution-independent coordinate sampling mechanism to generate watermarks pixel-wise, achieving ultra-high resolution watermark generation with fixed and limited memory and computational resources. This design ensures strong robustness in watermark extraction, even under extreme cropping and scaling distortions. Additionally, we introduce a hierarchical multi-scale coordinate embedding and a low-rank watermark injection strategy to ensure high-quality watermark generation and robust decoding. Experimental results demonstrate that our method significantly outperforms existing schemes in terms of both robustness and computational efficiency while preserving high image quality. Our approach achieves an accuracy greater than 98\% in watermark extraction with only 0. 4\% of the image area in 2K images. These results highlight the effectiveness of our method, making it a promising solution for large-scale and high-resolution image watermarking applications.

PDF Details

IJCAI Conference 2024 Conference Paper

Cross-modal Generation and Alignment via Attribute-guided Prompt for Unsupervised Text-based Person Retrieval

Zongyi Li
Jianbo Li
Yuxuan Shi
Hefei Ling
Jiazhong Chen
Runsheng Wang
Shijuan Huang

Text-based Person Search aims to retrieve a specified person using a given text query. Current methods predominantly rely on paired labeled image-text data to train the cross-modality retrieval model, necessitating laborious and time-consuming labeling. In response to this challenge, we present the Cross-modal Generation and Alignment via Attribute-guided Prompt framework (GAAP) for fully unsupervised text-based person search, utilizing only unlabeled images. Our proposed GAAP framework consists of two key parts: Attribute-guided Prompt Caption Generation and Attribute-guided Cross-modal Alignment module. The Attribute-guided Prompt Caption Generation module generates pseudo text labels by feeding the attribute prompts into a large-scale pre-trained vision-language model. These synthetic texts are then meticulously selected through a sample selection, ensuring the reliability for subsequent fine-tuning. The Attribute-guided Cross-modal Alignment module encompasses three sub-modules for feature alignment across modalities. Firstly, Cross-Modal Center Alignment (CMCA) aligns the samples with different modality centroids. Subsequently, to address ambiguity arising from local attribute similarities, an Attribute-guided Image-Text Contrastive Learning module (AITC) is proposed to facilitate the alignment of relationships among different pairs by considering local attribute similarities. Lastly, the Attribute-guided Image-Text Matching (AITM) module is introduced to mitigate noise in pseudo captions by using the image-attribute matching score to soften the hard matching labels. Empirical results showcase the effectiveness of our method across various text-based person search datasets under the fully unsupervised setting.

PDF Details DOI

ECAI Conference 2023 Conference Paper

Deep Unsupervised Hashing with Hyperbolic Multi-Structure Learning

Chuang Zhao 0001
Hefei Ling
Yuxuan Shi
Jiazhong Chen
Qiang Cao

Unsupervised hashing aims to learn a compact binary hash code to represent complex image content without label information. Existing deep unsupervised hashing methods typically first employ extracted image embeddings to construct semantic similarity structures and then map the images into compact hash codes while preserving the semantic similarity structure. However, the limited representation power of embeddings in Euclidean space and the inadequate exploration of the similarity structure in current methods often result in poorly discriminative hash codes. In this paper, we propose a novel method called Hyperbolic Multi-Structure Hashing (HMSH) to address these issues. Specifically, to increase the representation power of embeddings, we propose to map embeddings from Euclidean space to hyperbolic space and use the similarity structure constructed in hyperbolic space to guide hash learning. Meanwhile, to fully explore the structural information, we investigate four kinds of data structures, including local neighborhood structure, global clustering structure, inter/intra-class variation and variation under perturbation. Different data structures can complement each other, which is beneficial for hash learning. Extensive experimental results on three benchmark image datasets show that HMSH significantly outperforms state-of-the-art unsupervised hashing methods for image retrieval.

Details

IJCAI Conference 2023 Conference Paper

Detecting Adversarial Faces Using Only Real Face Self-Perturbations

Qian Wang
Yongqin Xian
Hefei Ling
Jinyuan Zhang
Xiaorui Lin
Ping Li
Jiazhong Chen
Ning Yu

Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when applied to facial recognition systems. Although existing defense techniques achieve high accuracy in detecting some specific adversarial faces (adv-faces), new attack methods especially GAN-based attacks with completely different noise patterns circumvent them and reach a higher attack success rate. Even worse, existing techniques require attack data before implementing the defense, making it impractical to defend newly emerging attacks that are unseen to defenders. In this paper, we investigate the intrinsic generality of adv-faces and propose to generate pseudo adv-faces by perturbing real faces with three heuristically designed noise patterns. We are the first to train an adv-face detector using only real faces and their self-perturbations, agnostic to victim facial recognition systems, and agnostic to unseen attacks. By regarding adv-faces as out-of-distribution data, we then naturally introduce a novel cascaded system for adv-face detection, which consists of training data self-perturbations, decision boundary regularization, and a max-pooling-based binary classifier focusing on abnormal local color aberrations. Experiments conducted on LFW and CelebA-HQ datasets with eight gradient-based and two GAN-based attacks validate that our method generalizes to a variety of unseen adversarial attacks.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification

Zongyi Li
Yuxuan Shi
Hefei Ling
Jiazhong Chen
Qian Wang
Fengfan Zhou

Person re-identification (Re-ID) based on unsupervised domain adaptation (UDA) aims to transfer the pre-trained model from one labeled source domain to an unlabeled target domain. Existing methods tackle this problem by using clustering methods to generate pseudo labels. However, pseudo labels produced by these techniques may be unstable and noisy, substantially deteriorating models’ performance. In this paper, we propose a Reliability Exploration with Self-ensemble Learning (RESL) framework for domain adaptive person Re- ID. First, to increase the feature diversity, multiple branches are presented to extract features from different data augmentations. Taking the temporally average model as a mean teacher model, online label refining is conducted by using its dynamic ensemble predictions from different branches as soft labels. Second, to combat the adverse effects of unreliable samples in clusters, sample reliability is estimated by evaluating the consistency of different clusters’ results, followed by selecting reliable instances for training and re-weighting sample contribution within Re-ID losses. A contrastive loss is also utilized with cluster-level memory features which are updated by the mean feature. The experiments demonstrate that our method can significantly surpass the state-of-the-art performance on the unsupervised domain adaptive person Re- ID.

PDF Details

TIST Journal 2017 Journal Article

Adult Image and Video Recognition by a Deep Multicontext Network and Fine-to-Coarse Strategy

Xinyu Ou
Hefei Ling
Han Yu
Ping Li
Fuhao Zou
Si Liu

Adult image and video recognition is an important and challenging problem in the real world. Low-level feature cues do not produce good enough information, especially when the dataset is very large and has various data distributions. This issue raises a serious problem for conventional approaches. In this article, we tackle this problem by proposing a deep multicontext network with fine-to-coarse strategy for adult image and video recognition. We employ a deep convolution networks to model fusion features of sensitive objects in images. Global contexts and local contexts are both taken into consideration and are jointly modeled in a unified multicontext deep learning framework. To make the model more discriminative for diverse target objects, we investigate a novel hierarchical method, and a task-specific fine-to-coarse strategy is designed to make the multicontext modeling more suitable for adult object recognition. Furthermore, some recently proposed deep models are investigated. Our approach is extensively evaluated on four different datasets. One dataset is used for ablation experiments, whereas others are used for generalization experiments. Results show significant and consistent improvements over the state-of-the-art methods.

Details DOI