Author name cluster

Zhiwei 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.

10 papers

1 author row

AAAI Conference 2026 Conference Paper

Image Content Matters: An Image Content Aware State Space Model for Accelerated MRI Reconstruction

Yucong Meng
Zhiwei Yang
Kexue Fu
Zhijian Song
Yonghong Shi

The challenge of accelerated MRI reconstruction lies in recovering high-quality images from undersampled k-space. Recently, the selective state space model (Mamba) has shown promising results in various tasks with balanced global receptive field and computational efficiency, shedding new light on MRI reconstruction. However, existing approaches directly flatten 2D images based on spatial positions and apply Mamba to vision tasks, failing to preserve and explore the content properties. In this paper, we posit that the key to unlocking Mamba's full potential for MRI reconstruction lies in content-aware sequence modeling. We investigate two fundamental challenges: (1) how to reasonably preserve semantic information when converting 2D images into 1D sequences, and (2) how to effectively identify and recover the crucial high-frequency textures. To this end, we introduce CAM, a novel framework that shifts Mamba-based MRI reconstruction from position-based to content-aware sequence modeling. Specifically, we introduce three modules: (1) the Semantic Preservation Scanning Module (SPSM) introduces learnable clustering centers to group similar pixels, establishing the semantic preserved sequence. (2) The Texture Extraction Scanning Module (TESM) acts as a differentiable local texture descriptor to estimate crucial high-frequency information, forming the texture emphasized sequence. (3) The Texture Enhancement Mamba Module (TEMM) further modulates the semantic sequence with texture-informed system matrices derived from the texture sequence, yielding both context- and texture-aware sequential representations. With these enhancements, CAM significantly outperforms existing methods across various datasets and under-sampling masks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Structural Entropy Guided Incremental Learning for Open-World Multimodal Social Event Detection

Zhiwei Yang
Haimei Qin
Xiaoyan Yu
Hao Peng
Lei Jiang
Li Sun
Zhiqin Yang

With the explosive growth of multimodal data streams on social media, the timely detection of emerging social events has become increasingly important. As a result, Multimodal Social Event Detection in open-world settings is receiving growing attention. However, most existing methods face two major limitations: (1) They overlook the dynamic nature of open-world social media data and fail to design dedicated incremental learning frameworks. (2) They ignore the impact of noise in streaming data, leading to performance degradation over long-term detection. To overcome these limitations, we propose SeInEvent (**S**tructural **E**ntropy Guided **In**cremental Learning for Open-World Multimodal Social **Event** Detection). Our innovations are as follows: **First**, considering data dynamics, we design a self-supervised alternating incremental contrastive learning mechanism. Through knowledge distillation, historical event clusters were reviewed and consolidated, and contrastive learning was combined to absorb knowledge of unknown events, ultimately achieving incremental learning without labels. **Second**, addressing the impact of noise, we propose a Pointwise Structural Entropy-based noise filter, which quantifies each sample’s informational contribution to the event clustering structure. It enables automatic removal of noisy data and supports robust long-term detection. Extensive experiments on two public datasets demonstrate that SeInEvent achieves superior performance.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification

Yucong Meng
Zhiwei Yang
Yonghong Shi
Zhijian Song

The accelerated MRI reconstruction process presents a challenging ill-posed inverse problem due to the extensive under-sampling in k-space. Recently, Vision Transformers (ViTs) have become the mainstream for this task, demonstrating substantial performance improvements. However, there are still three significant issues remain unaddressed: (1) ViTs struggle to capture high-frequency components of images, limiting their ability to detect local textures and edge information, thereby impeding MRI restoration; (2) Previous methods calculate multi-head self-attention (MSA) among both related and unrelated tokens in content, introducing noise and significantly increasing computational burden; (3) The naive feed-forward network in ViTs cannot model the multi-scale information that is important for image restoration. In this paper, we propose FPS-Former, a powerful ViT-based framework, to address these issues from the perspectives of frequency modulation, spatial purification, and scale diversification. Specifically, for issue (1), we introduce a frequency modulation attention module to enhance the self-attention map by adaptively re-calibrating the frequency information in a Laplacian pyramid. For issue (2), we customize a spatial purification attention module to capture interactions among closely related tokens, thereby reducing redundant or irrelevant feature representations. For issue (3), we propose an efficient feed-forward network based on a hybrid-scale fusion strategy. Comprehensive experiments conducted on three public datasets show that our FPS-Former outperforms state-of-the-art methods while requiring lower computational costs.

PDF Details DOI

EAAI Journal 2025 Journal Article

Feature super-resolution-based method for small-scale target detection and segmentation in side-scan sonar

Zhiwei Yang
Jianhu Zhao
Xi Zhao
Chao Huang

The application of side-scan sonar in underwater target detection plays a significant role in marine engineering construction and ocean resource exploration. However, existing methods for small object detection often suffer from limited accuracy and robustness. To address this issue, we propose a feature super-resolution-based approach for detecting and segmenting small targets in side-scan sonar images. During network training, a feature super-resolution branch is first constructed. Both low-level and high-level features from the backbone of the You Only Look Once (YOLO) network are fed into this branch. After processing through an encoder-decoder architecture, a super-resolved feature map is reconstructed, and the network is optimized via backpropagation to enhance the ability to extract features of small targets. Furthermore, an exponential decay strategy is adopted to define the loss weights of different branches, establishing a branch-aware training mechanism to improve training effectiveness. During inference, the super-resolution branch is discarded to balance detection accuracy and inference efficiency. Experimental results demonstrate that the proposed method achieves superior performance in detecting and segmenting small-scale targets in side-scan sonar imagery, achieving state-of-the-art results on two public side-scan sonar small object datasets. Additionally, this approach can be extended as a training strategy for side-scan sonar target detection and segmentation networks. The source code is available at https: //github. com/Yang-Code984/FSR_Sonar.

Details DOI

AAAI Conference 2025 Conference Paper

MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation

Zhiwei Yang
Yucong Meng
Kexue Fu
Shuo Wang
Zhijian Song

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the potential of LAM. Our findings suggest that imposing additional regularization on class-patch attention is necessary. To this end, we first view the attention as a novel directed graph and propose the Graph Category Representation module to implicitly regularize the interaction among class-patch entities. It ensures that class tokens dynamically condense the related patch information and suppress unrelated artifacts at a graph level. Second, motivated by the observation that CAM from classification weights maintains smooth localization of objects, we devise the Localization-informed Regularization module to explicitly regularize the class-patch attention. It directly mines the token relations from CAM and further supervises the consistency between class and patch tokens in a learnable manner. Extensive experiments on PASCAL VOC and MS COCO validate that MoRe effectively addresses the artifact issue and achieves state-of-the-art performance, surpassing recent single-stage and even multi-stage methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer

Zhiwei Yang
Chen Gao
Mike Zheng Shou

Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Previous methods typically rely on domain-specific training data and manual adjustments when applying to new scenarios and unseen anomaly types, suffering from high labor costs and limited generalization. Therefore, we aim to achieve generalist VAD, \ie, automatically handle any scene and any anomaly types without training data or human involvement. In this work, we propose PANDA, an agentic AI engineer based on MLLMs. Specifically, we achieve PANDA by comprehensively devising four key capabilities: (1) self-adaptive scene-aware strategy planning, (2) goal-driven heuristic reasoning, (3) tool-augmented self-reflection, and (4) self-improving chain-of-memory. Concretely, we develop a self-adaptive scene-aware RAG mechanism, enabling PANDA to retrieve anomaly-specific knowledge for anomaly detection strategy planning. Next, we introduce a latent anomaly-guided heuristic prompt strategy to enhance reasoning precision. Furthermore, PANDA employs a progressive reflection mechanism alongside a suite of context-aware tools to iteratively refine decision-making in complex scenarios. Finally, a chain-of-memory mechanism enables PANDA to leverage historical experiences for continual performance improvement. Extensive experiments demonstrate that PANDA achieves state-of-the-art performance in multi-scenario, open-set, and complex scenario settings without training and manual involvement, validating its generalizable and robust anomaly detection capability. Code is released at https: //github. com/showlab/PANDA.

PDF Details

AAAI Conference 2025 Conference Paper

Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space

Xiaoyan Yu
Yifan Wei
Shuaishuai Zhou
Zhiwei Yang
Li Sun
Hao Peng
Liehuang Zhu
Philip S. Yu

The vast, complex, and dynamic nature of social message data has posed challenges to social event detection (SED). Despite considerable effort, these challenges persist, often resulting in inadequately expressive message representations (ineffective) and prolonged learning durations (inefficient). In response to the challenges, this work introduces an unsupervised framework, HyperSED (Hyperbolic SED). Specifically, the proposed framework first models social messages into semantic-based message anchors, and then leverages the structure of the anchor graph and the expressiveness of the hyperbolic space to acquire structure- and geometry-aware anchor representations. Finally, HyperSED builds the partitioning tree of the anchor message graph by incorporating differentiable structural information as the reflection of the detected events. Extensive experiments on public datasets demonstrate HyperSED's competitive performance, along with a substantial improvement in efficiency compared to the current state-of-the-art unsupervised paradigm. Statistically, HyperSED boosts incremental SED by an average of 2%, 2%, and 25% in NMI, AMI, and ARI, respectively; enhancing efficiency by up to 37.41 times and at least 12.10 times, illustrating the advancement of the proposed framework.

PDF Details DOI

AAAI Conference 2023 Conference Paper

The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure

Xing Chen
Dongcui Diao
Hechang Chen
Hengshuai Yao
Haiyin Piao
Zhixiao Sun
Zhiwei Yang
Randy Goebel

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is "YES", and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in "off-policyness", according to an off-policy metric called DEON. Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservative Policy Iteration (CPI) objective better than PPO during training. To the best of our knowledge, all current PPO methods have the clipping operation and optimize in the clipped policy space. Our method is the first of this kind, which advances the understanding of CPI optimization and policy gradient methods. Code is available at https://github.com/raincchio/P3O.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Attention-based Multi-level Feature Fusion for Named Entity Recognition

Zhiwei Yang
Hechang Chen
Jiawei Zhang
Jing Ma
Yi Chang

Named entity recognition (NER) is a fundamental task in the natural language processing (NLP) area. Recently, representation learning methods (e. g. , character embedding and word embedding) have achieved promising recognition results. However, existing models only consider partial features derived from words or characters while failing to integrate semantic and syntactic information (e. g. , capitalization, inter-word relations, keywords, lexical phrases, etc. ) from multi-level perspectives. Intuitively, multi-level features can be helpful when recognizing named entities from complex sentences. In this study, we propose a novel framework called attention-based multi-level feature fusion (AMFF), which is used to capture the multi-level features from different perspectives to improve NER. Our model consists of four components to respectively capture the local character-level, global character-level, local word-level, and global word-level features, which are then fed into a BiLSTM-CRF network for the final sequence labeling. Extensive experimental results on four benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.

PDF Details DOI

AIIM Journal 2011 Journal Article

Multiple kernel learning in protein–protein interaction extraction from biomedical literature

Zhihao Yang
Nan Tang
Xiao Zhang
Hongfei Lin
Yanpeng Li
Zhiwei Yang

Objective Knowledge about protein–protein interactions (PPIs) unveils the molecular mechanisms of biological processes. The volume and content of published biomedical literature on protein interactions is expanding rapidly, making it increasingly difficult for interaction database administrators, responsible for content input and maintenance to detect and manually update protein interaction information. The objective of this work is to develop an effective approach to automatic extraction of PPI information from biomedical literature. Methods and materials We present a weighted multiple kernel learning-based approach for automatic PPI extraction from biomedical literature. The approach combines the following kernels: feature-based, tree, graph and part-of-speech (POS) path. In particular, we extend the shortest path-enclosed tree (SPT) and dependency path tree to capture richer contextual information. Results Our experimental results show that the combination of SPT and dependency path tree extensions contributes to the improvement of performance by almost 0. 7 percentage units in F-score and 2 percentage units in area under the receiver operating characteristics curve (AUC). Combining two or more appropriately weighed individual will further improve the performance. Both on the individual corpus and cross-corpus evaluation our combined kernel can achieve state-of-the-art performance with respect to comparable evaluations, with 64. 41% F-score and 88. 46% AUC on the AImed corpus. Conclusions As different kernels calculate the similarity between two sentences from different aspects. Our combined kernel can reduce the risk of missing important features. More specifically, we use a weighted linear combination of individual kernels instead of assigning the same weight to each individual kernel, thus allowing the introduction of each kernel to incrementally contribute to the performance improvement. In addition, SPT and dependency path tree extensions can improve the performance by including richer context information.

Details DOI