Tingfa Xu

Learn More
—Intuitively, instances of the same object category with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intra-category variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be(More)
We experimentally demonstrate a light-field moment microscopy (LFMM). The proposed technique employs a better estimation of the intensity derivative in solving the Poisson equation and therefore can significantly reduce the noise and error in the reconstructed light-field moment. The light field can be reconstructed then by using the moment, enabling the(More)
Modern deep neural network based object detection methods typically classify candidate proposals using their interior features. However, global and local surrounding contexts that are believed to be valuable for object detection are not fully exploited by existing methods yet. In this work, we take a step towards understanding what is a robust practice to(More)
Traditional total variation model leads to an undesirable staircase effect and is hard to eliminate high frequency noises in image restoration. In this paper, to solve this problem, a novel image restoration model based on adaptive total variation is proposed. A gradient fidelity term is coupled with adaptive total variation model. In order to choose proper(More)
During the process of moving object detection in an intelligent visual surveillance system, a scenario with complex background is sure to appear. The traditional methods, such as "frame difference" and "optical flow", may not able to deal with the problem very well. In such scenarios, we use a modified algorithm to do the background modeling work. In this(More)
In this paper, we propose a multi-view structural local subspace tracking algorithm based on sparse representation. We approximate the optimal state from three views: (1) the template view; (2) the PCA (principal component analysis) basis view; and (3) the target candidate view. Then we propose a unified objective function to integrate these three view(More)
This paper presents a recognition method to two words Chinese lexical for non-specific people using feature fusion of broadband and narrow-band spectrogram. In the process of image feature extraction, the image processing technique is applicable to the speech recognition field. First, equal width zoning line projection and binary width zoning line(More)
In this paper, we propose a novel hierarchical framework that combines motion and feature information to implement infrared-visible video registration on nearly planar scenes. In contrast to previous approaches, which involve the direct use of feature matching to find the global homography, the framework adds coarse registration based on the motion vectors(More)
Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple scales. However, the performance gain of such ad hoc architectures is usually limited to pay off the computational cost. In(More)
—Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are often ignored, which are actually useful for more accurate object detection. In this work, we propose a new EM-like(More)