Zhongyan Qiu

Learn More
Hard assignment-based bag of features (BoF) representation inevitably brings in quantization errors, which may lead to inaccuracy, even failure in object tracking. In this paper, we propose a novel soft-assigned BoF tracking approach, in which soft assignment is utilized to improve the robustness and discrimination of BoF representation. After labeling the(More)
Influenced by the utilized operation in implementation Influenced by the accuracy of depth Robust to resizing order and aspect ratios Basic idea: Combine region warping and region occlusion in an unified framework without image decomposition Image retargeting: content-aware adaption of image content to satisfy display screens, which should emphasize(More)
Bag of features (BoF) provides an effective and efficient representation for object tracking in video sequences. However, hard assignment used in BoF generation inevitably brings in quantization errors, which may lead to inaccuracy even failure in tracking. In this paper, we propose a novel soft-assigned bag of features tracking approach (SABoF), which can(More)
—Image retargeting aims to avoid visual distortion while retaining important image content in resizing. However, no single image retargeting method can handle all cases. In this paper, we propose a novel multi-operator image retargeting approach, which utilizes an efficient and human perception based automatic quality assessment in operator selection.(More)
  • 1