A Two-Stage Attentive Network for Single Image Super-Resolution

Abstract

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image superresolution (SISR) and contribute remarkable progress. However, most of the existing CNNs-based SISR methods do not adequately explore contextual information in the feature extraction stage and pay little attention to the final high-resolution (HR) image reconstruction step, hence hindering the desired SR performance. To address the above two issues, in this paper, we propose a twostage attentive network (TSAN) for accurate SISR in a coarse-tofine manner. Specifically, we design a novel multi-context attentive block (MCAB) to make the network focus on more informative contextual features. Moreover, we present an essential refined attention block (RAB) which could explore useful cues in HR space for reconstructing fine-detailed HR image. Extensive evaluations on four benchmark datasets demonstrate the efficacy of our proposed TSAN in terms of quantitative metrics and visual effects. Code is available at https://github.com/Jee-King/TSAN.

Multi-domain collaborative feature representation for robust visual object tracking

“…Visual object tracking is an important topic in computer vision, where the target object is identified in the first frame and tracked in all frames of a video. Due to the significant learning ability, deep convolutional neural networks (DCNNs) have been widely used to object detection [34,35,62], image matting [42,43,64], super-resolution [63,67,68], image enhancement [61,65] and visual object tracking [2,[11][12][13]15,19,22,28,32,33,38,47,58,[70][71][72]. However, RGB-based trackers suffer from bad environmental conditions, e.g., low illumination, fast motion, and so on.…”

CANet: A Context-Aware Network for Shadow Removal

“…Shadow is a natural phenomenon appearing when the light is partially or completely blocked. As a fundamental challenge in the field of computer vision, the existence of shadow in images or videos inevitably degrades the accuracy and effectiveness of general application tasks such as intrinsic image decomposition [21,10], visual recognition [25,17,24,14], object detection and tracking [28,1,2], trajectory prediction [27,33], single image super-resolution [40,39] and image captioning [6]. Therefore, shadow removal is important and necessary to im-prove the visual effects and avoid the performance drop on the above-mentioned computer vision tasks.…”

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking

“…Visual object tracking is an important topic in computer vision, where the target object is identified in the first frame and tracked in all frames of a video. Due to the significant learning ability, deep convolutional neural networks (DCNNs) have been widely used to object detection [35,34,62], image matting [43,42,64], super-resolution [68,67,63], image enhancement [61,65] and visual object tracking [2,15,19,28,32,72,38,13,70,71,22,12,11,33,58,47]. However, RGB-based trackers suffer from bad environmental conditions, e.g., low illumination, fast motion, and so on.…”