Related papers: Consistent-Point: Consistent Pseudo-Points for Sem…

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled…

Crowd counting in still images is a challenging problem in practice due to huge crowd-density variations, large perspective changes, severe occlusion, and variable lighting conditions. The state-of-the-art patch rescaling module (PRM) based…

Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are…

Change-point detection studies the problem of detecting the changes in the underlying distribution of the data stream as soon as possible after the change happens. Modern large-scale, high-dimensional, and complex streaming data call for…

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D…

Single image crowd counting is a challenging computer vision problem with wide applications in public safety, city planning, traffic management, etc. With the recent development of deep learning techniques, crowd counting has aroused much…

We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would like to have a crowd counting model specifically adapted to…

The aim of crowd counting is to estimate the number of people in images by leveraging the annotation of center positions for pedestrians' heads. Promising progresses have been made with the prevalence of deep Convolutional Neural Networks.…

Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists…

Many studies in data mining have proposed a new learning called semi-Supervised. Such type of learning combines unlabeled and labeled data which are hard to obtain. However, in unsupervised methods, the only unlabeled data are used. The…

We develop a Synthetic Fusion Pyramid Network (SPF-Net) with a scale-aware loss function design for accurate crowd counting. Existing crowd-counting methods assume that the training annotation points were accurate and thus ignore the fact…

Detection of change-points in a sequence of high-dimensional observations is a very challenging problem, and this becomes even more challenging when the sample size (i.e., the sequence length) is small. In this article, we propose some…

Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto statistical measures (MSE, MAE) exhibit large variance and…

Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes and severe congestion. Many methods only focus on the local appearance features and they cannot handle the aforementioned…

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose…

In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data. There is an emerging need to improve data efficiency for 3D tasks due to the scarcity of labeled 3D data. This paper…

Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the…

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…

In this paper, we study statistical inference of change-points (CPs) in multi-dimensional sequence. In CP detection from a multi-dimensional sequence, it is often desirable not only to detect the location, but also to identify the subset of…

Crowd analysis via computer vision techniques is an important topic in the field of video surveillance, which has wide-spread applications including crowd monitoring, public safety, space design and so on. Pixel-wise crowd understanding is…