Related papers: Zero-Shot Crowd Behavior Recognition
To alleviate the heavy annotation burden for training a reliable crowd counting model and thus make the model more practicable and accurate by being able to benefit from more data, this paper presents a new semi-supervised method based on…
Crowd behaviour analysis is essential to numerous real-world applications, such as public safety and urban planning, and therefore has been studied for decades. In the last decade or so, the development of deep learning has significantly…
Computer vision and machine learning have brought revolutionary shifts in perception for researchers, scientists, and the general populace. Once thought to be unattainable, these technologies have achieved the seemingly impossible. Their…
Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which…
Semi-supervised crowd counting is crucial for addressing the high annotation costs of densely populated scenes. Although several methods based on pseudo-labeling have been proposed, it remains challenging to effectively and accurately…
The existing crowd counting models require extensive training data, which is time-consuming to annotate. To tackle this issue, we propose a simple yet effective crowd counting method by utilizing the Segment-Everything-Everywhere Model…
This paper presents an approach to detect and track groups of people in video-surveillance applications, and to automatically recognize their behavior. This method keeps track of individuals moving together by maintaining a spacial and…
The severity of sustained injury resulting from assault-related violence can be minimised by reducing detection time. However, it has been shown that human operators perform poorly at detecting events found in video footage when presented…
We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the…
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to…
In this paper, we propose a method for real-time anomaly detection and localization in crowded scenes. Each video is defined as a set of non-overlapping cubic patches, and is described using two local and global descriptors. These…
Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge…
This paper presents two novel approaches for people counting in crowded and open environments that combine the information gathered by multiple views. Multiple camera are used to expand the field of view as well as to mitigate the problem…
In this paper we propose ResnetCrowd, a deep residual architecture for simultaneous crowd counting, violent behaviour detection and crowd density level classification. To train and evaluate the proposed multi-objective technique, a new 100…
A shortcoming of batch reinforcement learning is its requirement for rewards in data, thus not applicable to tasks without reward functions. Existing settings for lack of reward, such as behavioral cloning, rely on optimal demonstrations…
Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…
Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper…
Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual…
Current crowd counting algorithms are only concerned about the number of people in an image, which lacks low-level fine-grained information of the crowd. For many practical applications, the total number of people in an image is not as…
In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can…