Jingling Yuan

Huilin Zhu, Jingling Yuan, Xian Zhong et al.

Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-dataset differences while overlooking the intra-differences within the same dataset, leading to additional learning ambiguities. These domain-agnostic factors, e.g., density, surveillance perspective, and scale, can cause significant in-domain variations, and the misalignment of these factors across domains can lead to a drop in performance in cross-domain crowd counting. To address this issue, we propose a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains. The DAOT consists of three steps. First, individual-level differences in domain-agnostic factors are measured using structural similarity (SSIM). Second, the optimal transfer (OT) strategy is employed to smooth out these differences and find the optimal domain-to-domain misalignment, with outlier individuals removed via a virtual "dustbin" column. Third, knowledge is transferred based on the aligned domain-agnostic factors, and the model is retrained for domain adaptation to bridge the gap across domains. We conduct extensive experiments on five standard crowd-counting benchmarks and demonstrate that the proposed method has strong generalizability across diverse datasets. Our code will be available at: https://github.com/HopooLinZ/DAOT/.

Huilin Zhu, Jingling Yuan, Zhengwei Yang et al.

Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a critical challenge in current ZOC methods lies in their inability to identify high-quality exemplars effectively. This deficiency hampers scalability across diverse classes and undermines the development of strong visual associations between the identified classes and image content. To this end, we propose the Visual Association-based Zero-shot Object Counting (VA-Count) framework. VA-Count consists of an Exemplar Enhancement Module (EEM) and a Noise Suppression Module (NSM) that synergistically refine the process of class exemplar identification while minimizing the consequences of incorrect object identification. The EEM utilizes advanced vision-language pretaining models to discover potential exemplars, ensuring the framework's adaptability to various classes. Meanwhile, the NSM employs contrastive learning to differentiate between optimal and suboptimal exemplar pairs, reducing the negative effects of erroneous exemplars. VA-Count demonstrates its effectiveness and scalability in zero-shot contexts with superior performance on two object counting datasets.

Chong Lyu, Lin Li, Shiqing Wu et al.

The increasing utilization of large language models raises significant concerns about the propagation of social biases, which may result in harmful and unfair outcomes. However, existing debiasing methods treat the biased and unbiased samples independently, thus ignoring their mutual relationship. This oversight enables a hidden negative-positive coupling, where improvements for one group inadvertently compromise the other, allowing residual social bias to persist. In this paper, we introduce TriCon-Fair, a contrastive learning framework that employs a decoupled loss that combines triplet and language modeling terms to eliminate positive-negative coupling. Our TriCon-Fair assigns each anchor an explicitly biased negative and an unbiased positive, decoupling the push-pull dynamics and avoiding positive-negative coupling, and jointly optimizes a language modeling (LM) objective to preserve general capability. Experimental results demonstrate that TriCon-Fair reduces discriminatory output beyond existing debiasing baselines while maintaining strong downstream performance. This suggests that our proposed TriCon-Fair offers a practical and ethical solution for sensitive NLP applications.

Yujia Tong, Jingling Yuan, Tian Zhang et al.

Data-Free Quantization (DFQ) enables the quantization of Vision Transformers (ViTs) without requiring access to data, allowing for the deployment of ViTs on devices with limited resources. In DFQ, the quantization model must be calibrated using synthetic samples, making the quality of these synthetic samples crucial. Existing methods fail to fully capture and balance the global and local features within the samples, resulting in limited synthetic data quality. Moreover, we have found that during inference, there is a significant difference in the distributions of intermediate layer activations between the quantized and full-precision models. These issues lead to a severe performance degradation of the quantized model. To address these problems, we propose a pipeline for Data-Free Quantization for Vision Transformers (DFQ-ViT). Specifically, we synthesize samples in order of increasing difficulty, effectively enhancing the quality of synthetic data. During the calibration and inference stage, we introduce the activation correction matrix for the quantized model to align the intermediate layer activations with those of the full-precision model. Extensive experiments demonstrate that DFQ-ViT achieves remarkable superiority over existing DFQ methods and its performance is on par with models quantized through real data. For example, the performance of DeiT-T with 3-bit weights quantization is 4.29% higher than the state-of-the-art. Our method eliminates the need for fine-tuning, which not only reduces computational overhead but also lowers the deployment barriers for edge devices. This characteristic aligns with the principles of Green Learning by improving energy efficiency and facilitating real-world applications in resource-constrained environments.

Peiliang Zhang, Jingling Yuan, Qing Xie et al.

Molecular Relational Learning (MRL) is widely applied in natural sciences to predict relationships between molecular pairs by extracting structural features. The representational similarity between substructure pairs determines the functional compatibility of molecular binding sites. Nevertheless, aligning substructure representations by attention mechanisms lacks guidance from chemical knowledge, resulting in unstable model performance in chemical space (\textit{e.g.}, functional group, scaffold) shifted data. With theoretical justification, we propose the \textbf{Re}presentational \textbf{Align}ment with Chemical Induced \textbf{Fit} (ReAlignFit) to enhance the stability of MRL. ReAlignFit dynamically aligns substructure representation in MRL by introducing chemical Induced Fit-based inductive bias. In the induction process, we design the Bias Correction Function based on substructure edge reconstruction to align representations between substructure pairs by simulating chemical conformational changes (dynamic combination of substructures). ReAlignFit further integrates the Subgraph Information Bottleneck during fit process to refine and optimize substructure pairs exhibiting high chemical functional compatibility, leveraging them to generate molecular embeddings. Experimental results on nine datasets demonstrate that ReAlignFit outperforms state-of-the-art models in two tasks and significantly enhances model's stability in both rule-shifted and scaffold-shifted data distributions.

Yao Deng, Xian Zhong, Wenxuan Liu et al.

RGB cameras excel at capturing rich texture details with high spatial resolution, whereas event cameras offer exceptional temporal resolution and a high dynamic range (HDR). Leveraging their complementary strengths can substantially enhance object tracking under challenging conditions, such as high-speed motion, HDR environments, and dynamic background interference. However, a significant spatio-temporal asymmetry exists between these two modalities due to their fundamentally different imaging mechanisms, hindering effective multi-modal integration. To address this issue, we propose {Hierarchical Asymmetric Distillation} (HAD), a multi-modal knowledge distillation framework that explicitly models and mitigates spatio-temporal asymmetries. Specifically, HAD proposes a hierarchical alignment strategy that minimizes information loss while maintaining the student network's computational efficiency and parameter compactness. Extensive experiments demonstrate that HAD consistently outperforms state-of-the-art methods, and comprehensive ablation studies further validate the effectiveness and necessity of each designed component. The code will be released soon.

Yujia Tong, Tian Zhang, Jingling Yuan et al.

Vision Transformers (ViTs) have revolutionized computer vision tasks with their exceptional performance. However, the introduction of privacy regulations such as GDPR and CCPA has brought new challenges to them. These laws grant users the right to withdraw their data, necessitating not only the deletion of data but also the complete removal of its influence from trained models. Machine unlearning emerges as a critical solution, with exact unlearning being computationally prohibitive and approximate methods offering a more practical approach. This work addresses the particularly challenging scenario of random data forgetting in ViTs, where the model must forget specific samples while retaining others, even within the same class. We first reveal the core characteristics of ViTs through selective masking experiments: when high-attention areas are masked, the model retains its recognition capability but significantly weakens its memorization ability. Based on the above insights, we propose LetheViT, a contrastive unlearning method tailored for ViTs. LetheViT uses masked image inputs to generate positive logits and original image inputs to generate negative logits, guiding the model to forget specific details while retaining the general cl category outlines. Experimental results demonstrate that LetheViT achieves state-of-the-art performance, effectively balancing privacy compliance with model efficacy.

Huilin Zhu, Senyao Li, Jingling Yuan et al.

Expanding pre-trained zero-shot counting models to handle unseen categories requires more than simply adding new prompts, as this approach does not achieve the necessary alignment between text and visual features for accurate counting. We introduce RichCount, the first framework to address these limitations, employing a two-stage training strategy that enhances text encoding and strengthens the model's association with objects in images. RichCount improves zero-shot counting for unseen categories through two key objectives: (1) enriching text features with a feed-forward network and adapter trained on text-image similarity, thereby creating robust, aligned representations; and (2) applying this refined encoder to counting tasks, enabling effective generalization across diverse prompts and complex images. In this manner, RichCount goes beyond simple prompt expansion to establish meaningful feature alignment that supports accurate counting across novel categories. Extensive experiments on three benchmark datasets demonstrate the effectiveness of RichCount, achieving state-of-the-art performance in zero-shot counting and significantly enhancing generalization to unseen categories in open-world scenarios.

Huilin Zhu, Jingling Yuan, Zhengwei Yang et al.

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific outputs, leading to inaccuracies when such outputs are required. These inaccuracies stem from two key challenges: 1) the prevalence of single-category images in datasets, which leads models to generalize specific categories as representative of all objects, and 2) the use of mean squared error loss during training, which applies uniform penalization. This uniform penalty disregards errors in less frequent categories, particularly when these errors contribute minimally to the overall loss. To address these issues, we propose {FocalCount}, a novel approach that leverages diverse feature attributes to estimate the number of object categories in an image. This estimate serves as a weighted factor to correct class-count imbalances. Additionally, we introduce {Focal-MSE}, a new loss function that integrates binary cross-entropy to generate stronger error gradients, enhancing the model's sensitivity to errors in underrepresented categories. Our approach significantly improves the model's ability to distinguish between specific classes and general counts, demonstrating superior performance and scalability in both few-shot and zero-shot scenarios across three object counting datasets. The code will be released soon.

Xiaohua Wu, Lin Li, Xiaohui Tao et al.

Happiness computing based on large-scale online web data and machine learning methods is an emerging research topic that underpins a range of issues, from personal growth to social stability. Many advanced Machine Learning (ML) models with explanations are used to compute the happiness online assessment while maintaining high accuracy of results. However, domain knowledge constraints, such as the primary and secondary relations of happiness factors, are absent from these models, which limits the association between computing results and the right reasons for why they occurred. This article attempts to provide new insights into the explanation consistency from an empirical study perspective. Then we study how to represent and introduce domain knowledge constraints to make ML models more trustworthy. We achieve this through: (1) proving that multiple prediction models with additive factor attributions will have the desirable property of primary and secondary relations consistency, and (2) showing that factor relations with quantity can be represented as an importance distribution for encoding domain knowledge. Factor explanation difference is penalized by the Kullback-Leibler divergence-based loss among computing models. Experimental results using two online web datasets show that domain knowledge of stable factor relations exists. Using this knowledge not only improves happiness computing accuracy but also reveals more significative happiness factors for assisting decisions well.

Donghang Pan, Jingling Yuan, Lin Li et al.

The growing prosperity of social networks has brought great challenges to the sentimental tendency mining of users. As more and more researchers pay attention to the sentimental tendency of online users, rich research results have been obtained based on the sentiment classification of explicit texts. However, research on the implicit sentiment of users is still in its infancy. Aiming at the difficulty of implicit sentiment classification, a research on implicit sentiment classification model based on deep neural network is carried out. Classification models based on DNN, LSTM, Bi-LSTM and CNN were established to judge the tendency of the user's implicit sentiment text. Based on the Bi-LSTM model, the classification model of word-level attention mechanism is studied. The experimental results on the public dataset show that the established LSTM series classification model and CNN classification model can achieve good sentiment classification effect, and the classification effect is significantly better than the DNN model. The Bi-LSTM based attention mechanism classification model obtained the optimal R value in the positive category identification.

Chengyao Du, Jingling Yuan, Jiansheng Dong et al.

Panoramic video is a sort of video recorded at the same point of view to record the full scene. With the development of video surveillance and the requirement for 3D converged video surveillance in smart cities, CPU and GPU are required to possess strong processing abilities to make panoramic video. The traditional panoramic products depend on post processing, which results in high power consumption, low stability and unsatisfying performance in real time. In order to solve these problems,we propose a real-time panoramic video stitching framework.The framework we propose mainly consists of three algorithms, LORB image feature extraction algorithm, feature point matching algorithm based on LSH and GPU parallel video stitching algorithm based on CUDA.The experiment results show that the algorithm mentioned can improve the performance in the stages of feature extraction of images stitching and matching, the running speed of which is 11 times than that of the traditional ORB algorithm and 639 times than that of the traditional SIFT algorithm. Based on analyzing the GPU resources occupancy rate of each resolution image stitching, we further propose a stream parallel strategy to maximize the utilization of GPU resources. Compared with the L-ORB algorithm, the efficiency of this strategy is improved by 1.6-2.5 times, and it can make full use of GPU resources. The performance of the system accomplished in the paper is 29.2 times than that of the former embedded one, while the power dissipation is reduced to 10W.

Minglong Qi, Shengwu Xiong, Jingling Yuan et al.

Linear codes with a few weights have important applications in authentication codes, secret sharing, consumer electronics, etc.. The determination of the parameters such as Hamming weight distributions and complete weight enumerators of linear codes are important research topics. In this paper, we consider some classes of linear codes with a few weights and determine the complete weight enumerators from which the corresponding Hamming weight distributions are derived with help of some sums involving Legendre symbol.

Minglong Qi, Shengwu Xiong, Jingling Yuan et al.

In this paper, the formulas of some exponential sums over finite field, related to the Coulter's polynomial, are settled based on the Coulter's theorems on Weil sums, which may have potential application in the construction of linear codes with few weights.

Minglong Qi, Shenwu Xiong, Jingling Yuan

In this paper, a new class of frequency hopping sequences (FHSs) of length $ p^{n} $ is constructed by using Ding-Helleseth generalized cyclotomic classes of order 2, of which the Hamming auto- and cross-correlation functions are investigated (for the Hamming cross-correlation, only the case $ p\equiv 3\pmod 4 $ is considered). It is shown that the set of the constructed FHSs is optimal with respect to the average Hamming correlation functions.

Minglong Qi, Shengwu Xiong, Jingling Yuan et al.

Pseudorandom binary sequences with optimal balance and autocorrelation have many applications in stream cipher, communication, coding theory, etc. It is known that binary sequences with three-level autocorrelation should have an almost difference set as their characteristic sets. How to construct new families of almost difference set is an important research topic in such fields as communication, coding theory and cryptography. In a work of Ding, Helleseth, and Martinsen in 2001, the authors developed a new method, known as the Ding-Helleseth-Martinsens Constructions in literature, of constructing an almost difference set from product sets of GF(2) and the union of two cyclotomic classes of order four. In the present paper, we have constructed two classes of almost difference set with product sets between GF(2) and union sets of the cyclotomic classes of order 12 using that method. In addition, we could find there do not exist the Ding-Helleseth-Martinsens Constructions for the cyclotomic classes of order six and eight.

Minglong Qi, Shengwu Xiong, Jingling Yuan et al.

In this paper, the linear complexity over $\mathbf{GF}(r)$ of generalized cyclotomic quaternary sequences with period $2pq$ is determined, where $ r $ is an odd prime such that $r \ge 5$ and $r\notin \lbrace p,q\rbrace$. The minimal value of the linear complexity is equal to $\tfrac{5pq+p+q+1}{4}$ which is greater than the half of the period $2pq$. According to the Berlekamp-Massey algorithm, these sequences are viewed as enough good for the use in cryptography. We show also that if the character of the extension field $\mathbf{GF}(r^{m})$, $r$, is chosen so that $\bigl(\tfrac{r}{p}\bigr) = \bigl(\tfrac{r}{q}\bigr) = -1$, $r\nmid 3pq-1$, and $r\nmid 2pq-4$, then the linear complexity can reach the maximal value equal to the length of the sequences.