Skip to main content

and
  1. No Access

    Article

    Efficient Fourier-Based Approach for Detecting Orientations and Occlusions in Epipolar Plane Images for 3D Scene Modeling

    This paper presents a Fourier-based approach for automatically constructing a 3D panoramic model of a natural scene from a video sequence. The video sequences could be captured by an unstabilized camera mounte...

    Zhigang Zhu, Guangyou Xu, Xueyin Lin in International Journal of Computer Vision (2005)

  2. No Access

    Article

    Modeling and Representations of Large-Scale 3D Scenes

    Zhigang Zhu, Takeo Kanade in International Journal of Computer Vision (2008)

  3. No Access

    Article

    Harnessing Lab Knowledge for Real-World Action Recognition

    Much research on human action recognition has been oriented toward the performance gain on lab-collected datasets. Yet real-world videos are more diverse, with more complicated actions and often only a few of ...

    Zhigang Ma, Yi Yang, Fei** Nie, Nicu Sebe in International Journal of Computer Vision (2014)

  4. No Access

    Article

    Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization

    As a way to relieve the tedious work of manual annotation, active learning plays important roles in many applications of visual concept recognition. In typical active learning scenarios, the number of labelled...

    Yi Yang, Zhigang Ma, Fei** Nie, **aojun Chang in International Journal of Computer Vision (2015)

  5. No Access

    Article

    Bounding Multiple Gaussians Uncertainty with Application to Object Tracking

    This paper proves the uncertainty bound for the multiple Gaussian functions, termed multiple Gaussians Uncertainty (MGU), which significantly generalizes the uncertainty principle for the single Gaussian funct...

    Baochang Zhang, Alessandro Perina, Zhigang Li in International Journal of Computer Vision (2016)