Zhao Xie

Beyond shape: incorporating color invariance into a biologically inspired feedforward model of category recognition

Being lack of theoretical support from biological cues in computer vision, current computational and learning approaches of object categorization mostly aim at better performances neglecting analysis on framework in human brain for visual information processing materially which cause little-marginal improvement and more complexity. Focusing on the uncertainty of color mechanism in visual cortex and motivating from biological issues on shape information, we present the model incorporating color invariant descriptors and plausible shape feature biologically to formulate the robust representation of each category with only simple SVM classifier to achieve the amazing performance. Our model has the characteristics of illumination, scale, position, orientation, viewpoint invariance, and competitive with current algorithms on only a few training examples from several data sets, including Caltech 101 and GRAZ for category recognition. Also, experimental results show the robustness when challenged by noisy or blurred images.

Robust tracking with per-exemplar support vector machine

The authors extend exemplar representation to the field of tracking and propose a robust tracking algorithm with per-exemplar support vector machine (SVM) classifiers. First, the authors train the simple yet effective exemplar SVM classifier using the target object as the single positive and mining its surroundings as hard negatives. Second, the authors propose an online ensemble tracker, which integrates the useful ‘key historical templates’ of the target to refine the current template, leading to better discriminative power of tracker and effectively decreasing the risk of drift. Experiments on challenging sequences demonstrate that the tracker performs well in accuracy and robustness, especially under the sequences with strong illumination variation and scale variation, as well as pose change and partial occlusion in the long-time sequence.

Brief survey on image semantic analysis and understanding

Semantic issues are highly concerned with high-level interpretation in image understanding, which include text-image gap and its own affinity. Concentrating on text-formatting with entities in images, three sophisticated methodologies are roundly reviewed as generative, discriminative and descriptive grammar on the basis of contextual features. The following objective benchmark for visual words is also directly presented for semantic coherency. Finally, the summarized directions on semantics in image understanding are discussed intensively for further researches.

Visual-semantic collaborative interactions in synergic system for scene modeling

With the reference of slaving principles from synergetic in physics, the embedding correspondences from visual cues and semantic ones are captured as prototypes in dynamic system. In scene modeling for interpretation, collaborative visual-semantic interactions are factorized as self-stimulation, self-restraint and other-restraint processes with decrease of energy to stable situation. The experiments demonstrate our framework can automatically correct false local labels and improve the accuracy of scene categorization.

FCM in novel application of science and technology progress monitor system

This paper focuses on the issues about the complex relations in large-scale FCM, and then proposes a promising method for weight global optimization with local inference to analyze and predict indexes in Anhui sci-tech progress monitor system. Firstly, a new concept, unbalanced degree, is introduced for standard evaluation in FCM model to modify the weight assessment factors and result in the satisfied convergence rate. Secondly, relations between unbalanced degree and convergence error are also presented for further analysis with training error and guarantee on perfect condition in model. Thirdly, local inference in FCM is discussed to enhance prediction accuracy rate. Finally, experimental result reveals successful application of FCM in large-scale complex sci-tech systems.