Related papers: RipViz: Finding Rip Currents by Learning Pathline …
This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting…
When learning from streaming data, a change in the data distribution, also known as concept drift, can render a previously-learned model inaccurate and require training a new model. We present an adaptive learning algorithm that extends…
Particle Image Velocimetry (PIV) has become increasingly popular to study structures in turbulent flows. PIV allows direct extraction and investigation of spatial structures in the given flow field. Increasing temporal resolution of PIV…
This work considers identifying parameters characterizing a physical system's dynamic motion directly from a video whose rendering configurations are inaccessible. Existing solutions require massive training data or lack generalizability to…
In many sports, it is useful to analyse video of an athlete in competition for training purposes. In swimming, stroke rate is a common metric used by coaches; requiring a laborious labelling of each individual stroke. We show that using a…
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to…
This work proposes a mmWave radar's scene flow estimation framework supervised by data from a widespread visual-inertial (VI) sensor suite, allowing crowdsourced training data from smart vehicles. Current scene flow estimation methods for…
Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of…
We study recovering fluid density and velocity from sparse multiview videos. Existing neural dynamic reconstruction methods predominantly rely on optical flows; therefore, they cannot accurately estimate the density and uncover the…
The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes. Current techniques that utilize neural rendering for facilitating free-view videos…
Video stylization plays a key role in content creation, but it remains a challenging problem. Na\"ively applying image stylization frame-by-frame hurts temporal consistency and reduces style richness. Alternatively, training a dedicated…
One of the oldest flow visualization techniques is through multiple pathlines generated by the movement of seeding particles spatially distributed in the flow. In the computerized era, particle images are used in quantitative measurements,…
Detecting the transition from laminar to turbulent flow in particulate pipe systems remains a complex issue in fluid dynamics, often requiring sophisticated and costly experimental apparatus. This research presents an innovative streak…
Optical flow is a fundamental technique for motion estimation, widely applied in video stabilization, interpolation, and object tracking. Traditional optical flow estimation methods rely on restrictive assumptions like brightness constancy…
Visually-induced motion sickness (VIMS), a side effect of perceived motion caused by visual stimulation, is a major obstacle to the widespread use of Virtual Reality (VR). Along with scene object information, visual stimulation can be…
Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level, assuming objects are rigid bodies. However, these instance-level methods are…
Efficiently modeling dynamic motion information in videos is crucial for action recognition task. Most state-of-the-art methods heavily rely on dense optical flow as motion representation. Although combining optical flow with RGB frames as…
Human motion sensing plays a crucial role in smart systems for decision-making, user interaction, and personalized services. Extensive research that has been conducted is predominantly based on cameras, whose intrusive nature limits their…
A novel algorithm to detect road lanes in videos, called recursive video lane detector (RVLD), is proposed in this paper, which propagates the state of a current frame recursively to the next frame. RVLD consists of an intra-frame lane…
In the US, thousands of Pan, Tilt, and Zoom (PTZ) traffic cameras monitor highway conditions. There is a great interest in using these highway cameras to gather valuable road traffic data to support traffic analysis and decision-making for…