Skip to main content

7 Result(s)

within Tianshan Liu Remove this filter

and

  1. No Access

    Article

    Collaborative model with adaptive selection scheme for visual tracking

    Visual tracking is a challenging task since it involves develo** an effective appearance model to deal with numerous factors. In this paper, we propose a robust object tracking algorithm based on a collabora...

    Tianshan Liu, Jun Kong, Min Jiang… in International Journal of Machine Learning … (2019)

  2. No Access

    Article

    Spatiotemporal attention enhanced features fusion network for action recognition

    In recent years, action recognition has become a popular and challenging task in computer vision. Nowadays, two-stream networks with appearance stream and motion stream can make judgment jointly and get excell...

    Danfeng Zhuang, Min Jiang, Jun Kong… in International Journal of Machine Learning … (2021)

  3. No Access

    Article

    Building Energy Consumption Prediction Based on Temporal-Aware Attention and Energy Consumption States

    Accurate energy consumption prediction helps to achieve more reasonable power system design, and is of great significance to energy saving and power safety. As the main input feature of traditional prediction ...

    Qi Zhang, Jun Kong, Min Jiang, Tianshan Liu in Journal of Electrical Engineering & Techno… (2023)

  4. No Access

    Article

    Heterogeneous dual network with feature consistency for domain adaptation person re-identification

    To reduce the noisy pseudo-labels generated by clustering for unsupervised domain adaptation (UDA) person re-identification (re-ID), the method of collaborative training between dual networks has been proposed...

    Hua Zhou, Jun Kong, Min Jiang, Tianshan Liu in International Journal of Machine Learning … (2023)

  5. No Access

    Article

    Multi-stream ternary enhanced graph convolutional network for skeleton-based action recognition

    A novel mechanism for skeleton-based action recognition is proposed in this paper by enhancing and fusing diverse skeleton features from distinct levels. Graph convolutional neural networks (GCNs) have been pr...

    Jun Kong, Shengquan Wang, Min Jiang, TianShan Liu in Neural Computing and Applications (2023)

  6. Article

    Open Access

    Category-Aware Saliency Enhance Learning Based on CLIP for Weakly Supervised Salient Object Detection

    Weakly supervised salient object detection (SOD) using image-level category labels has been proposed to reduce the annotation cost of pixel-level labels. However, existing methods mostly train a classification...

    Yunde Zhang, Zhili Zhang, Tianshan Liu, Jun Kong in Neural Processing Letters (2024)

    Download PDF (1870 KB) View Article

  7. No Access

    Article

    Part-pixel transformer with smooth alignment fusion for domain adaptation person re-identification

    The method of generating pseudo-labels by clustering is proved to be effective in unsupervised domain adaptation (UDA) person re-identification (re-ID). However, the pseudo-labels contain a lot of noise, which...

    Jun Kong, Hua Zhou, Min Jiang, Tianshan Liu in Signal, Image and Video Processing (2024)