An Adaptive Descriptor Design for Object Recognition in the Wild

  title={An Adaptive Descriptor Design for Object Recognition in the Wild},
  author={Zhenyu Guo and Z. Wang},
  journal={2013 IEEE International Conference on Computer Vision},
  • Zhenyu Guo, Z. Wang
  • Published 2013
  • Computer Science
  • 2013 IEEE International Conference on Computer Vision
  • Digital images nowadays show large appearance variabilities on picture styles, in terms of color tone, contrast, vignetting, and etc. These `picture styles' are directly related to the scene radiance, image pipeline of the camera, and post processing functions (e.g., photography effect filters). Due to the complexity and nonlinearity of these factors, popular gradient-based image descriptors generally are not invariant to different picture styles, which could degrade the performance for object… CONTINUE READING
    4 Citations
    Feature weighting with augmented visual phrase in visual product recognition
    • Highly Influenced
    Photo Filter Recommendation by Category-Aware Aesthetic Learning
    • 22
    • PDF
    Modality-Invariant Image Classification Based on Modality Uniqueness and Dictionary Learning
    • 4
    • Highly Influenced
    • PDF


    Kernel Descriptors for Visual Recognition
    • 341
    • PDF
    Distinctive Image Features from Scale-Invariant Keypoints
    • D. Lowe
    • Computer Science
    • International Journal of Computer Vision
    • 2004
    • 8,621
    • PDF
    On feature combination for multiclass object classification
    • 877
    • PDF
    Deformation and illumination invariant feature point descriptor
    • 49
    • PDF
    Speeded-Up Robust Features (SURF)
    • 10,615
    • PDF
    Learning Local Image Descriptors
    • 363
    • PDF
    Efficient Match Kernel between Sets of Features for Visual Recognition
    • 246
    • PDF
    Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
    • S. Lazebnik, C. Schmid, J. Ponce
    • Computer Science
    • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
    • 2006
    • 8,082
    • PDF
    Cross-Domain Object Recognition Via Input-Output Kernel Analysis
    • 21
    • PDF
    Adapting Visual Category Models to New Domains
    • 1,506
    • Highly Influential
    • PDF