Related papers: DenseBox: Unifying Landmark Localization with End …

Convolutional Neural Networks (CNN) have demon- strated its successful applications in computer vision, speech recognition, and natural language processing. For object recog- nition, CNNs might be limited by its strict label requirement and…

Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images,…

Computing at the edge offers intriguing possibilities for the development of autonomy and artificial intelligence. The advancements in autonomous technologies and the resurgence of computer vision have led to a rise in demand for fast and…

The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames. Standard motion estimators used in tracking, e.g., Long Short Term Memory (LSTM), only deal with single…

Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further…

Street view images classification aiming at urban land use analysis is difficult because the class labels (e.g., commercial area), are concepts with higher abstract level compared to the ones of general visual tasks (e.g., persons and…

Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to…

Object detection has compelling applications over a range of domains, including human-computer interfaces, security and video surveillance, navigation and road traffic monitoring, transportation systems, industrial automation healthcare,…

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The…

At present, the performance of deep neural network in general object detection is comparable to or even surpasses that of human beings. However, due to the limitations of deep learning itself, the small proportion of feature pixels, and the…

The detection of abnormal behaviours in crowded scenes has to deal with many challenges. This paper presents an efficient method for detection and localization of anomalies in videos. Using fully convolutional neural networks (FCNs) and…

Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature. Estimating 3D coordinates for each pixel on the object surface holds great potential as it provides dense 2D-3D geometric…

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…

This work proposed a novel learning objective to train a deep neural network to perform end-to-end image pixel clustering. We applied the approach to instance segmentation, which is at the intersection of image semantic segmentation and…

A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can…

In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of times, our FC-CNN is…

Co-localization is the problem of localizing objects of the same class using only the set of images that contain them. This is a challenging task because the object detector must be built without negative examples that can lead to more…

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…

One-stage detector basically formulates object detection as dense classification and localization. The classification is usually optimized by Focal Loss and the box location is commonly learned under Dirac delta distribution. A recent trend…

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and…