Related papers: Exploring Descriptions of Movement Through Geovisu…

We developed a machine vision system to automatically capture the dynamics of pedestrians under four different traffic scenarios. By considering the overhead view of each pedestrian as a digital object, the system processes the image…

This paper introduces a novel approach to enhance existing motion captioning methods, which directly map representations of movement to high-level descriptive captions (e.g., ``a person doing jumping jacks"). The existing methods require…

Event-based vision sensors, such as the Dynamic Vision Sensor (DVS), are ideally suited for real-time motion analysis. The unique properties encompassed in the readings of such sensors provide high temporal resolution, superior sensitivity…

Forecasting human trajectories is critical for tasks such as robot crowd navigation and autonomous driving. Modeling social interactions is of great importance for accurate group-wise motion prediction. However, most existing methods do not…

Understanding how people move in the urban area is important for solving urbanization issues, such as traffic management, urban planning, epidemic control, and communication network improvement. Leveraging recent availability of large…

We introduce MotionScript, a novel framework for generating highly detailed, natural language descriptions of 3D human motions. Unlike existing motion datasets that rely on broad action labels or generic captions, MotionScript provides…

Moving Object Segmentation (MOS) aims to discover, segment, and track objects that move independently of the camera. Current MOS methods, however, exhibit two fundamental limitations: they rely on pre-computed 2D auxiliary modalities such…

Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this paper, we present a new pose-based convolutional neural network model…

In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since…

Human mobility clustering is an important problem for understanding human mobility behaviors (e.g., work and school commutes). Existing methods typically contain two steps: choosing or learning a mobility representation and applying a…

The prediction of surrounding agents' motion is a key for safe autonomous driving. In this paper, we explore navigation maps as an alternative to the predominant High Definition (HD) maps for learning-based motion prediction. Navigation…

Thanks to the rise of wearable and connected devices, sensor-generated time series comprise a large and growing fraction of the world's data. Unfortunately, extracting value from this data can be challenging, since sensors report low-level…

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

Co-speech gestures play a vital role in non-verbal communication. In this paper, we introduce a new framework for co-speech gesture understanding in the wild. Specifically, we propose three new tasks and benchmarks to evaluate a model's…

We present Lang2Motion, a framework for language-guided point trajectory generation by aligning motion manifolds with joint embedding spaces. Unlike prior work focusing on human motion or video synthesis, we generate explicit trajectories…

Predicting human motion is critical for assistive robots and AR/VR applications, where the interaction with humans needs to be safe and comfortable. Meanwhile, an accurate prediction depends on understanding both the scene context and human…

Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual…

Binary silhouettes and keypoint-based skeletons have dominated human gait recognition studies for decades since they are easy to extract from video frames. Despite their success in gait recognition for in-the-lab environments, they usually…

The information collected by mobile phone operators can be considered as the most detailed information on human mobility across a large part of the population. The study of the dynamics of human mobility using the collected geolocations of…

In the past decade, large scale mobile phone data have become available for the study of human movement patterns. These data hold an immense promise for understanding human behavior on a vast scale, and with a precision and accuracy never…