Related papers: Strip R-CNN: Large Strip Convolution for Remote Se…

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN). However, Conv2d is vulnerable to image corruptions and adversarial samples. It is…

Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well…

Table structure recognition (TSR) aims to convert tabular images into a machine-readable format, where a visual encoder extracts image features and a textual decoder generates table-representing tokens. Existing approaches use classic…

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement and a lightweight model built from a large number of the depth-wise…

It has been well recognized that modeling object-to-object relations would be helpful for object detection. Nevertheless, the problem is not trivial especially when exploring the interactions between objects to boost video object detectors.…

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and classification are decoupled. To obtain the detection score for an RoI, we multiply the objectness score with the fine-grained classification…

Recent advances in visual tracking showed that deep Convolutional Neural Networks (CNN) trained for image classification can be strong feature extractors for discriminative trackers. However, due to the drastic difference between image…

Recently, deep learning technology have been extensively used in the field of image recognition. However, its main application is the recognition and detection of ordinary pictures and common scenes. It is challenging to effectively and…

3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that…

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model…

Image representations derived from pre-trained Convolutional Neural Networks (CNNs) have become the new state of the art in computer vision tasks such as instance retrieval. This work explores the suitability for instance retrieval of…

Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in…

Object detection is a challenging task in remote sensing because objects only occupy a few pixels in the images, and the models are required to simultaneously learn object locations and detection. Even though the established approaches well…

Action recognition is a key algorithmic part of emerging on-the-edge smart video surveillance and security systems. Skeleton-based action recognition is an attractive approach which, instead of using RGB pixel data, relies on human pose…

Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel…

Convolutional neural networks (CNNs) have long been the cornerstone of target detection, but they are often limited by limited receptive fields, which hinders their ability to capture global contextual information. We re-examined the…

Convolutional Neural Networks (CNNs) have been consistently proved state-of-the-art results in image Super-Resolution (SR), representing an exceptional opportunity for the remote sensing field to extract further information and knowledge…

3D object detection from LiDAR data for autonomous driving has been making remarkable strides in recent years. Among the state-of-the-art methodologies, encoding point clouds into a bird's eye view (BEV) has been demonstrated to be both…