Jinglin Xu

Jinglin Xu

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 April 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
JHJunwei Han
Junwei Han
JXJinglin Xu
Jinglin Xu
FNFeiping Nie
Feiping Nie
XLXuelong Li
Xuelong Li
Recently, many real-world applications exploit multi-view data, which is collected from diverse domains or obtained from various feature extractors and reflect different properties or distributions of the data. In this work, a novel unsupervised multi-view framework is proposed to cluster such data. The proposed method, called Multi-View clustering with Adaptive Sparse Memberships and Weight Allocation (MVASM), pays more attention to constructing a common membership matrix with proper sparseness over different views and learns the centroid matrix and its corresponding weight of each view. Concretely, MVASM method attempts to learn a common and flexible sparse membership matrix to indicate the clustering, which explores the underlying consensus information of multiple views, and solves the multiple centroid matrices and weights to utilize the view-specific information and further modifies the above-mentioned membership matrix. In addition, the theoretical analysis, including the determination of the power exponent parameter, convergence analysis, and complexity analysis are also presented. Compared to the state-of-the-art methods, the proposed method improves the performance of clustering on different public datasets and demonstrates its reasonability and superiority.

11 March 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
JXJinglin Xu
Jinglin Xu
JHJunwei Han
Junwei Han
FNFeiping Nie
Feiping Nie
XLXuelong Li
Xuelong Li
With explosive growth of data, the multi-view data is widely used in many fields, such as data mining, machine learning, computer vision and so on. Because such data always has complex structure, i.e. many categories, many perspectives of description and high dimension, how to formulate an accurate and reliable framework for multi-view classification is a very challenging task. In this paper, we propose a novel multi-view classification method by using multiple multi-class support vector machines (SVMs) and a novel collaborative strategy. Here each multi-class SVM integrates the scaling factor to renewedly adjust the weight allocation which is beneficial to highlight some more discriminative features. Furthermore, we use the decision function values of multiple learners to combine multiple multi-class learners, and then determine the final classification results according to a final confidence score. In addition, through a series of theoretical analyses, we bridge the proposed model with the solvable problem and solve it by an iterative optimization method with convergence. We evaluate the proposed method on several image datasets and face datasets, and the experimental results demonstrate that our proposed method performs better than other state-of-the-art learning algorithms.

1 April 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JXJinglin Xu
Jinglin Xu
SYSibo Yin
Sibo Yin
YPYuxin Peng
Yuxin Peng
Existing action quality assessment (AQA) methods mainly learn deep representations at the video level to score diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they suffer from low credibility and accuracy, thus insufficient for stringent applications, such as competitive sports and sports injury rehabilitation. We argue that a fine-grained understanding of actions requires the model to parse actions in semantics, time, and space, which is the key to the credibility and accuracy of the AQA technique. Based on this insight, we propose a new human-centric fine-grained action quality assessment method named Unified Fine-grained spatial-temporal action Parser, namely Uni-FineParser. It learns human-centric foreground action representations by focusing on target action regions within each frame and exploiting their fine-grained alignments in semantics, time, and space, minimizing the impact of invalid backgrounds during the assessment. In addition, we construct human-centric foreground action mask annotations for the FineDiving, AQA-7, and MTL-AQA datasets, respectively called FineDiving-HM, AQA-7-HM, and MTL-AQA-HM. With refined spatio-temporal annotations on diverse target action procedures, Uni-FineParser can provide a potential for human-centric fine-grained action quality assessment with better interpretability. Through extensive experiments, we demonstrate the effectiveness of Uni-FineParser, which outperforms state-of-the-art methods while supporting more tasks of human-centric action understanding.

14 July 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
JXJinglin Xu
Jinglin Xu
YRYongming Rao
Yongming Rao
JZJie Zhou
Jie Zhou
JLJiwen Lu
Jiwen Lu

18 September 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
HSHongbo Sun
Hongbo Sun
XHXiangteng He
Xiangteng He
JXJinglin Xu
Jinglin Xu
YPYuxin Peng
Yuxin Peng
Fine-grained visual categorization (FGVC) aims to distinguish visual objects from multiple subcategories of the coarse-grained category. Subtle inter-class differences among various subcategories make the FGVC task more challenging. Existing methods primarily focus on learning salient visual patterns while ignoring how to capture the object’s internal structure, causing difficulty in obtaining complete discriminative regions within the object to limit FGVC performance. To address the above issue, we propose a Structure Information Mining and Object-aware Feature Enhancement (SIM-OFE) method for fine-grained visual categorization, which explores the visual object’s internal structure composition and appearance traits. Concretely, we first propose a simple yet effective hybrid perception attention module for locating visual objects based on global-scope and local-scope significance analyses. Then, a structure information mining module is proposed to model the distribution and context relation of critical regions within the object, highlighting the whole object and discriminative regions for distinguishing subtle differences. Finally, an object-aware feature enhancement module is proposed to combine global-scope and local-scope discriminative features in an attentive coupling way for powerful visual representations in fine-grained recognition. Extensive experiments on three FGVC benchmark datasets demonstrate that our proposed SIM-OFE method can achieve state-of-the-art performance.

7 April 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
JXJinglin Xu
Jinglin Xu
GCGuangyi Chen
Guangyi Chen
NZNuoxing Zhou
Nuoxing Zhou
WZWei-Shi Zheng
Wei-Shi Zheng
JLJiwen Lu
Jiwen Lu
Humans have the inherent advantage of understanding action intention, while it is an enormous challenge to train the machine to localize unintentional action in videos due to the lack of reliable annotations for stable training. The annotations of unintentional action are unreliable since different annotators are affected by their subjective appraisals and intrinsic ambiguity, which brings heavy difficulties for the training. To address this issue, we propose a probabilistic framework for unintentional action localization by modeling the uncertainty of annotations. Our framework consists of two main components, including Temporal Label Aggregation (TLA) and Dense Probabilistic Localization (DPL). We first formulate each annotated failure moment as a temporal label distribution. Then we propose a TLA component to aggregate temporal label distributions of different failure moments in an online manner and generate dense probabilistic supervision. Based on TLA, We further develop a DPL component to jointly train three heads (i.e., probabilistic dense classification, probabilistic temporal detection, and probabilistic regression) with different supervision granularities and make them highly collaborative. We evaluate our approach on the largest unintentional action dataset OOPS and demonstrate that our approach can achieve significant improvement over the baseline and state-of-the-art methods.