Related papers: A Foreground Inference Network for Video Surveilla…

Deep convolutional networks have achieved the state-of-the-art for semantic image segmentation tasks. However, training these networks requires access to densely labeled images, which are known to be very expensive to obtain. On the other…

Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing…

With the advancement of remote-sensed imaging large volumes of very high resolution land cover images can now be obtained. Automation of object recognition in these 2D images, however, is still a key issue. High intra-class variance and low…

Street-view image has been widely applied as a crucial mobile mapping data source. The inpainting of street-view images is a critical step for street-view image processing, not only for the privacy protection, but also for the urban…

Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various…

During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual…

Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within…

We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions. During sampling, residual…

Transfer learning is widely used for training machine learning models. Here, we study the role of transfer learning for training fully convolutional networks (FCNs) for medical image segmentation. Our experiments show that although transfer…

Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses. A key to address this problem is to localize discriminative parts to extract pose-invariant features.…

Depression is a prevalent global mental health disorder, characterised by persistent low mood and anhedonia. However, it remains underdiagnosed because current diagnostic methods depend heavily on subjective clinical assessments. To enable…

Visual tracking is intrinsically a temporal problem. Discriminative Correlation Filters (DCF) have demonstrated excellent performance for high-speed generic visual object tracking. Built upon their seminal work, there has been a plethora of…

Conditional Random Rields (CRF) have been widely applied in image segmentations. While most studies rely on hand-crafted features, we here propose to exploit a pre-trained large convolutional neural network (CNN) to generate deep features…

Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results,…

Deep learning usually requires large amounts of labeled training data, but annotating data is costly and tedious. The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data…

For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…

Generating natural language descriptions for in-the-wild videos is a challenging task. Most state-of-the-art methods for solving this problem borrow existing deep convolutional neural network (CNN) architectures (AlexNet, GoogLeNet) to…

Face detection has achieved great success using the region-based methods. In this report, we propose a region-based face detector applying deep networks in a fully convolutional fashion, named Face R-FCN. Based on Region-based Fully…

Change Detection is a crucial but extremely challenging task of remote sensing image analysis, and much progress has been made with the rapid development of deep learning. However, most existing deep learning-based change detection methods…

Fully convolutional network (FCN) is a seminal work for semantic segmentation. However, due to its limited receptive field, FCN cannot effectively capture global context information which is vital for semantic segmentation. As a result, it…