Related papers: Zero-Shot Crowd Behavior Recognition

Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in…

The performance of machine learning model can be further improved if contextual cues are provided as input along with base features that are directly related to an inference task. In offline learning, one can inspect historical training…

Crowdsourcing provides a practical way to obtain large amounts of labeled data at a low cost. However, the annotation quality of annotators varies considerably, which imposes new challenges in learning a high-quality model from the…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

Few/Zero-shot learning is a big challenge of many classifications tasks, where a classifier is required to recognise instances of classes that have very few or even no training samples. It becomes more difficult in multi-label…

Full body trackers are utilized for surveillance and security purposes, such as person-tracking robots. In the Middle East, uniform crowd environments are the norm which challenges state-of-the-art trackers. Despite tremendous improvements…

Machine learning systems are increasingly deployed in high-stakes domains, yet they remain vulnerable to bias systematic disparities that disproportionately impact specific demographic groups. Traditional bias detection methods often depend…

Sequence labeling is a fundamental framework for various natural language processing problems. Its performance is largely influenced by the annotation quality and quantity in supervised learning scenarios, and obtaining ground truth labels…

We address the problem of anomaly detection in videos. The goal is to identify unusual behaviours automatically by learning exclusively from normal videos. Most existing approaches are usually data-hungry and have limited generalization…

Zero-shot skeleton-based action recognition aims to recognize actions of unseen categories after training on data of seen categories. The key is to build the connection between visual and semantic space from seen to unseen classes. Previous…

Recent progress towards designing models that can generalize to unseen domains (i.e domain generalization) or unseen classes (i.e zero-shot learning) has embarked interest towards building models that can tackle both domain-shift and…

Large-scale annotated datasets allow AI systems to learn from and build upon the knowledge of the crowd. Many crowdsourcing techniques have been developed for collecting image annotations. These techniques often implicitly rely on the fact…

Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…

We consider the problem of recovering a single person's 3D human mesh from in-the-wild crowded scenes. While much progress has been in 3D human mesh estimation, existing methods struggle when test input has crowded scenes. The first reason…

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes…

Understanding human behaviour in crowded indoor environments is central to surveillance, smart buildings, and human-robot interaction, yet existing datasets rarely capture real-world indoor complexity at scale. We introduce IndoorCrowd, a…

A large part of the current success of deep learning lies in the effectiveness of data -- more precisely: labelled data. Yet, labelling a dataset with human annotation continues to carry high costs, especially for videos. While in the image…

Crowd counting is to estimate the number of objects (e.g., people or vehicles) in an image of unconstrained congested scenes. Designing a general crowd counting algorithm applicable to a wide range of crowd images is challenging, mainly due…

Zero-shot learning methods typically assume that the new, unseen classes encountered during deployment come from the same distribution as the the classes in the training set. However, real-world scenarios often involve class distribution…

Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…