Author name cluster

Meng Yang

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.

15 papers

1 author row

AAAI Conference 2026 Conference Paper

RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection

Rui Ding
Zhaonian Kuang
Zongwei Zhou
Meng Yang
Xinhu Zheng
Gang Hua

Multi-view 3D detection with bird’s eye view (BEV) is crucial for autonomous driving and robotics, but its robustness in real-world is limited as it struggles to predict accurate depth values. A mainstream solution, cross-modal distillation, transfers depth information from LiDAR to camera models but also unintentionally transfers depth-irrelevant information (e.g. LiDAR density). To mitigate this issue, we propose RayD3D, which transfers crucial depth knowledge along the ray: a line projecting from the camera to true location of an object. It is based on the fundamental imaging principle that predicted location of this object can only vary along this ray, which is finally determined by predicted depth value. Therefore, distilling along the ray enables more effective depth information transfer. More specifically, we design two ray-based distillation modules. Ray-based Contrastive Distillation (RCD) incorporates contrastive learning into distillation by sampling along the ray to learn how LiDAR accurately locates objects. Ray-based Weighted Distillation (RWD) adaptively adjusts distillation weight based on the ray to minimize the interference of depth-irrelevant information in LiDAR. For validation, we widely apply RayD3D into three representative types of BEV-based models, including BEVDet, BEVDepth4D, and BEVFormer. Our method is trained on clean NuScenes, and tested on both clean NuScenes and RoboBEV with a variety types of data corruptions. Our method significantly improves the robustness of all the three base models in all scenarios without increasing inference costs, and achieves the best when compared to recently released multi-view and distillation models.

PDF Details DOI

EAAI Journal 2025 Journal Article

Distributed long-time series prediction based on multiple feature decomposition and federated meta-learning under data heterogeneity

Meng Yang
Shuyuan Zhang
Zhanzhong Wang
Shuoqi Wang

Accurate and efficient traffic flow prediction is essential for intelligent transportation systems management. Traditional prediction methods have limited performance in capturing time dependent feature, especially in long time series prediction. Deep learning has limited improvement on this problem and also leads to poor model generalization due to data heterogeneity. Therefore, we propose a distributed long time series prediction framework. It primarily focuses on the enhancement of client-side local models in distributed long time series forecasting. On the one hand, in order to capture the characteristics of the client data, we design a novel multidimensional decomposition module to process the data as input to the subsequent model. To effectively address seasonality and periodicity of long time series forecasting, we propose a backbone forecasting model based on the Patch-Mixer architecture. On the other hand, to enhance the model's generalization capability across diverse tasks, we introduce an enhanced Model-Agnostic Meta-Learning (MAML) framework with improved adaptation mechanisms. This mechanism enables each client model to rapidly adapt to its local tasks through parameter distribution from the server. Furthermore, we propose an acceleration strategy based on Fast Local Initialization (FLI) to optimize the training efficiency of local models. Finally, a real heterogeneous inter-city traffic flow dataset is taken to verify the effectiveness of the proposed method. Experimental results demonstrate that our proposed method outperforms the baseline models across multiple evaluation metrics.

Details DOI

EAAI Journal 2025 Journal Article

Identification of surface subsidence risk in deep foundation pits using a Mamba fusion model

Chenhe Ge
Pengfei Li
Mingju Zhang
Meng Yang

This study proposes a novel artificial intelligence–driven neural network model, CNN-Mamba-LSTM-SA, for predicting surface settlement induced by deep foundation pit excavation. The model integrates Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), a Self-Attention (SA) mechanism, and the Mamba architecture to capture both spatial and long-range temporal dependencies in multi-source monitoring data. Bayesian optimization is employed for hyperparameter tuning, and Variational Mode Decomposition (VMD) is used for data denoising, resulting in improved prediction accuracy. To enhance model interpretability, Shapley Additive Explanations (SHAP) are applied to identify key deformation drivers, revealing groundwater level and building settlement as the most influential factors. Model performance is validated using monitoring data from the Nanjing Gemini excavation project, where it achieves superior results compared to conventional models. The CNN-Mamba-LSTM-SA model reduces Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) by up to 69. 77 %, 62. 45 %, and 79. 45 %, respectively. Further analysis through ablation experiments confirms the contribution of each module. Interestingly, the combined removal of CNN and SA results in greater performance degradation than the sum of their individual effects. Finally, a risk warning framework is developed to enable the dynamic transformation of predicted and observed settlement values into actionable risk levels. This integrated artificial intelligence approach offers a robust and interpretable tool for managing excavation-induced risks in urban geotechnical engineering.

Details DOI

IJCAI Conference 2025 Conference Paper

Multimodal Image Matching Based on Cross-Modality Completion Pre-training

Meng Yang
Fan Fan
Jun Huang
Yong Ma
Xiaoguang Mei
Zhanchuan Cai
Jiayi Ma

The differences in imaging devices cause multimodal images to have modal differences and geometric distortions, complicating the matching task. Deep learning-based matching methods struggle with multimodal images due to the lack of large annotated multimodal datasets. To address these challenges, we propose XCP-Match based on cross-modality completion pre-training. XCP-Match has two phases. (1) Self-supervised cross-modality completion pre-training based on real multimodal image dataset. We develop a novel pre-training model to learn cross-modal semantic features. The pre-training uses masked image modeling method for cross-modality completion, and introduces an attention-weighted contrastive loss to emphasize matching in overlapping areas. (2) Supervised fine-tuning for multimodal image matching based on the augmented MegaDepth dataset. XCP-Match constructs a complete matching framework to overcome geometric distortions and achieve precise matching. Two-phase training encourages the model to learn deep cross-modal semantic information, improving adaptation to modal differences without needing large annotated datasets. Experiments demonstrate that XCP-Match outperforms existing algorithms on public datasets.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

A Consistency and Integration Model with Adaptive Thresholds for Weakly Supervised Object Localization

Hao Su
Meng Yang

Weakly Supervised Object Localization (WSOL) is a challenging task, which aims to learn object localization with less costly image-level labels. Existing convolution neural network (CNN) based methods tend to focus on discriminative regions of objects, while transformer-based methods overemphasize deep global features powerful for classification and lack the capability to perceive object details, leading to prediction results far from the object boundary. In this paper, we propose a novel Consistency and Integration Model with Adaptive Thresholds (CIAT) that exploits the spatial-semantic consistency between shallow and deep features to activate more object regions and detects the object regions adaptively in different images. First, we introduce a simple plug-and-play consistency and integration module of shallow-deep features (CISD), which utilizes shallow features efficiently to enhance the entire object perception. Then, we design an online adaptive threshold (OAT) based on Bayesian decision theory, which computes a reasonable segmentation threshold adaptive for the localization map of each image, making the predicted bounding box closer to the ground truth. Extensive experiments on two widely used CUB-200-2011 and ILSVRC datasets verify the effectiveness of our methods.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception

Yuzhe Ji
Yijie Chen
Liuqing Yang
Rui Ding
Meng Yang
Xinhu Zheng

Recent advancements in 3D perception have led to a proliferation of network architectures, particularly those involving multi-modal fusion algorithms. While these fusion algorithms improve accuracy, their complexity often impedes real-time performance. This paper introduces VeXKD, an effective and Versatile framework that integrates Cross-Modal Fusion with Knowledge Distillation. VeXKD applies knowledge distillation exclusively to the Bird's Eye View (BEV) feature maps, enabling the transfer of cross-modal insights to single-modal students without additional inference time overhead. It avoids volatile components that can vary across various 3D perception tasks and student modalities, thus improving versatility. The framework adopts a modality-general cross-modal fusion module to bridge the modality gap between the multi-modal teachers and single-modal students. Furthermore, leveraging byproducts generated during fusion, our BEV query guided mask generation network identifies crucial spatial locations across different BEV feature maps in a data-driven manner, significantly enhancing the effectiveness of knowledge distillation. Extensive experiments on the nuScenes dataset demonstrate notable improvements, with up to 6. 9\%/4. 2\% increase in mAP and NDS for 3D detection tasks and up to 4. 3\% rise in mIoU for BEV map segmentation tasks, narrowing the performance gap with multi-modal models.

PDF Details DOI

EAAI Journal 2023 Journal Article

An unsupervised neural network for graphical health index construction and residual life prediction

Zhen Li
Tao Tao
Meng Yang
Jibin Wang
Zhuo Chen
Jianguo Wu

To better characterize the health status and performing remaining useful life prediction, a composite health index is developed through the fusion of multi-channel signals. However, most of the existing literature limits the data fusion to be linear, which implies that the underlying degradation pattern must follow a linear form. This strong prerequisite of these approaches undermines the effectiveness of existing techniques for capturing the potential nonlinear nature of degradation process. In order to overcome this limitation as well as to improve the predictability, this paper proposes a nonlinear health index construction method achieving by an unsupervised neural network. Specifically, a neural network structure is introduced to approximate the highly nonlinear relationship between signals and health status. Furthermore, we consider the remaining useful life prediction as a binary classification problem, and then propose a maximal classification margin constraint, which is integrated with the monotonicity and minimal variability at the failure time to formulate the novel loss function. To estimate the model parameter, we developed a customized adaptive moment estimation algorithm (Adam). The comprehensive case study is performed based on the benchmark C-MAPSS dataset. As reported in the experiment, the constructed health index can better characterize the underlying degradation process.

Details DOI

EAAI Journal 2023 Journal Article

Deep learning-based real-time 3D human pose estimation

Xiaoyan Zhang
Zhengchun Zhou
Ying Han
Hua Meng
Meng Yang
Sutharshan Rajasegarar

Human body pose estimation represented by joint rotations is essential for driving the virtual characters. The present paper developed a novel end-to-end point-to-pose mesh fitting network (P2P-MeshNet) to directly estimate the body joint rotations. P2P-MeshNet provided a strong collaboration between the deep learning network, an inverse kinematics network for body pose estimation (IKNet-body), and the self-correcting network, an iterative error feedback network (IEF). The introduced P2P-MeshNet was then applied to the free mocap (FreeMocap) dataset covering OpenPose 3D joint locations reconstructed from multi-view OpenPose 2D joint locations. The generated joint rotations were tested using the mean per joint position error (MPJPE), as well as the percentage of correct keypoints (PCK) along with the area under the PCK curve (AUC) with a threshold range of 0–60 mm after Procrustes aligned. Based on the compared metrics, P2P-MeshNet with 11. 31 mm and 99. 7% in estimate error and success rate as well as an AUC of 80. 9 demonstrated a more consistent tool for future human body pose estimation. The runtime performance of 100 frames per second implied its potential application prospects.

Details DOI

YNICL Journal 2021 Journal Article

Brain iron assessment in patients with First-episode schizophrenia using quantitative susceptibility mapping

Man Xu
Yihao Guo
Junying Cheng
Kangkang Xue
Meng Yang
Xueqin Song
Yanqiu Feng
Jingliang Cheng

PURPOSE: Decreased serum ferritin level was recently found in schizophrenia. Whether the brain iron concentration in schizophrenia exists abnormality is of research significance. Quantitative susceptibility mapping (QSM) was used in this study to assess brain iron changes in the grey matter nuclei of patients with first-episode schizophrenia. METHODS: * was evaluated using receiver operating characteristic curve. The correlations between regional iron variations and clinical PANSS (Positive and Negative Syndrome Scale) scores were assessed using partial correlation analysis. RESULTS: * values did not show significant correlations with PANSS scores (p > 0.05). CONCLUSION: * in the evaluation of schizophrenia-related brain iron changes. It demonstrated that QSM may be a potential biomarker for further understanding the pathophysiological mechanism of first-episode schizophrenia.

Details DOI

AAAI Conference 2021 System Paper

Integrating Pre-trained Model into Rule-based Dialogue Management

Jun Quan
Meng Yang
Qiang Gan
Deyi Xiong
Yiming Liu
Yuchen Dong
Fangxin Ouyang
Jun Tian

Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility. However, it is hard for developers to maintain the dialogue logic when the scenarios get more and more complex. On the other hand, data-driven dialogue systems, usually with end-to-end structures, are popular in academic research and easier to deal with complex conversations, but such methods require plenty of training data and the behaviors are less interpretable. In this paper, we propose a method to leverages the strength of both rule-based and data-driven dialogue managers (DM). We firstly introduce the DM of Carina Dialog System (CDS, an advanced industrial dialogue system built by Microsoft). Then we propose the “modeltrigger” design to make the DM trainable thus scalable to scenario changes. Furthermore, we integrate pre-trained models and empower the DM with few-shot capability. The experimental results demonstrate the effectiveness and strong fewshot capability of our method.

PDF Details

AAAI Conference 2020 Conference Paper

Hierarchical Attention Network with Pairwise Loss for Chinese Zero Pronoun Resolution

Peiqin Lin
Meng Yang

Recent neural network methods for Chinese zero pronoun resolution didn’t take bidirectional attention between zero pronouns and candidate antecedents into consideration, and simply treated the task as a classiﬁcation task, ignoring the relationship between different candidates of a zero pronoun. To solve these problems, we propose a Hierarchical Attention Network with Pairwise Loss (HAN-PL), for Chinese zero pronoun resolution. In the proposed HAN-PL, we design a two-layer attention model to generate more powerful representations for zero pronouns and candidate antecedents. Furthermore, we propose a novel pairwise loss by introducing the correct-antecedent similarity constraint and the pairwisemargin loss, making the learned model more discriminative. Extensive experiments have been conducted on OntoNotes 5. 0 dataset, and our model achieves state-of-the-art performance in the task of Chinese zero pronoun resolution.

PDF Details

AAAI Conference 2020 Conference Paper

Learning Saliency-Free Model with Generic Features for Weakly-Supervised Semantic Segmentation

Wenfeng Luo
Meng Yang

Current weakly-supervised semantic segmentation methods often estimate initial supervision from class activation maps (CAM), which produce sparse discriminative object seeds and rely on image saliency to provide background cues when only class labels are used. To eliminate the demand of extra data for training saliency detector, we propose to discover class pattern inherent in the lower layer convolution features, which are scarcely explored as in previous CAM methods. Speciﬁcally, we ﬁrst project the convolution features into a low-dimension space and then decide on a decision boundary to generate class-agnostic maps for each semantic category that exists in the image. Features from Lower layer are more generic, thus capable of generating proxy ground-truth with more accurate and integral objects. Experiments on the PAS- CAL VOC 2012 dataset show that the proposed saliency-free method outperforms the previous approaches under the same weakly-supervised setting and achieves superior segmentation results, which are 64. 5% on the validation set and 64. 6% on the test set concerning mIoU metric.

PDF Details

IJCAI Conference 2019 Conference Paper

Deep Mask Memory Network with Semantic Dependency and Context Moment for Aspect Level Sentiment Classification

Peiqin Lin
Meng Yang
Jianhuang Lai

Aspect level sentiment classification aims at identifying the sentiment of each aspect term in a sentence. Deep memory networks often use location information between context word and aspect to generate the memory. Although improved results are achieved, the relation information among aspects in the same sentence is ignored and the word location can't bring enough and accurate information for the analysis on the aspect sentiment. In this paper, we propose a novel framework for aspect level sentiment classification, deep mask memory network with semantic dependency and context moment (DMMN-SDCM), which integrates semantic parsing information of the aspect and the inter-aspect relation information into deep memory network. With the designed attention mechanism based on semantic dependency information, different parts of the context memory in different computational layers are selected and useful inter-aspect information in the same sentence is exploited for the desired aspect. To make full use of the inter-aspect relation information, we also jointly learn a context moment learning task, which aims to learn the sentiment distribution of the entire sentence for providing a background for the desired aspect. We examined the merit of our model on SemEval 2014 Datasets, and the experimental results show that our model achieves a state-of-the-art performance.

PDF Details

AAAI Conference 2017 Conference Paper

Discriminative Semi-Supervised Dictionary Learning with Entropy Regularization for Pattern Classification

Meng Yang
Lin Chen

Dictionary learning has played an important role in the success of sparse representation, which triggers the rapid developments of unsupervised and supervised dictionary learning methods. However, in most practical applications, there are usually quite limited labeled training samples while it is relatively easy to acquire abundant unlabeled training samples. Thus semi-supervised dictionary learning that aims to effectively explore the discrimination of unlabeled training data has attracted much attention of researchers. Although various regularizations have been introduced in the prevailing semi-supervised dictionary learning, how to design an effective unified model of dictionary learning and unlabeled-data class estimating and how to well explore the discrimination in the labeled and unlabeled data are still open. In this paper, we propose a novel discriminative semisupervised dictionary learning model (DSSDL) by introducing discriminative representation, an identical coding of unlabeled data to the coding of testing data final classification, and an entropy regularization term. The coding strategy of unlabeled data can not only avoid the affect of its incorrect class estimation, but also make the learned discrimination be well exploited in the final classification. The introduced regularization of entropy can avoid overemphasizing on some uncertain estimated classes for unlabeled samples. Apart from the enhanced discrimination in the learned dictionary by the discriminative representation, an extended dictionary is used to mainly explore the discrimination embedded in the unlabeled data. Extensive experiments on face recognition, digit recognition and texture classification show the effectiveness of the proposed method.

PDF Details

AAAI Conference 2016 Conference Paper

Analysis-Synthesis Dictionary Learning for Universality-Particularity Representation Based Classification

Meng Yang
Weiyang Liu
Weixin Luo
Linlin Shen

Dictionary learning has played an important role in the success of sparse representation. Although synthesis dictionary learning for sparse representation has been well studied for universality representation (i. e. , the dictionary is universal to all classes) and particularity representation (i. e. , the dictionary is class-particular), jointly learning an analysis dictionary and a synthesis dictionary is still in its infant stage. Universality-particularity representation can well match the intrinsic characteristics of data (i. e. , different classes share commonality and distinctness), while analysis-synthesis dictionary can give a more complete view of data representation (i. e. , analysis dictionary is a dual-viewpoint of synthesis dictionary). In this paper, we proposed a novel model of analysis-synthesis dictionary learning for universalityparticularity (ASDL-UP) representation based classiﬁcation. The discrimination of universality and particularity representation is jointly exploited by simultaneously learning a pair of analysis dictionary and synthesis dictionary. More specifically, we impose a label preserving term to analysis coding coefﬁcients for universality representation. Fisher-like regularizations for analysis coding coefﬁcients and the subsequent synthesis representation are introduced to particularity representation. Compared with other state-of-the-art dictionary learning methods, ASDL-UP has shown better or competitive performance in various classiﬁcation tasks.

PDF Details