Related papers: GPU-accelerated SIFT-aided source identification o…
Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…
We present a deep neural network (DNN) that uses both sensor data (gyroscope) and image content (optical flow) to stabilize videos through unsupervised learning. The network fuses optical flow with real/virtual camera pose histories into a…
Videos are a popular media form, where online video streaming has recently gathered much popularity. In this work, we propose a novel method of real-time video stabilization - transforming a shaky video to a stabilized video as if it were…
Photo Response Non-Uniformity (PRNU) based source camera attribution is an effective method to determine the origin camera of visual media (an image or a video). However, given that modern devices, especially smartphones, capture images,…
This communication is about an application of image forensics where we use camera sensor fingerprints to identify source camera (SCI: Source Camera Identification) in webcam videos. Sensor or camera fingerprints are based on computing the…
Surveillance footage represents a valuable resource and opportunities for conducting gait analysis. However, the typical low quality and high noise levels in such footage can severely impact the accuracy of pose estimation algorithms, which…
Multimedia Forensics allows to determine whether videos or images have been captured with the same device, and thus, eventually, by the same person. Currently, the most promising technology to achieve this task, exploits the unique traces…
Object recognition from live video streams comes with numerous challenges such as the variation in illumination conditions and poses. Convolutional neural networks (CNNs) have been widely used to perform intelligent visual object…
Real-time video surveillance has become a crucial technology for smart cities, made possible through the large-scale deployment of mobile and fixed video cameras. In this paper, we propose situation-aware streaming, for real-time…
Previous deep learning-based video stabilizers require a large scale of paired unstable and stable videos for training, which are difficult to collect. Traditional trajectory-based stabilizers, on the other hand, divide the task into…
Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.…
When applied sequentially to video, frame-based networks often exhibit temporal inconsistency - for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this…
Camera fingerprints are precious tools for a number of image forensics tasks. A well-known example is the photo response non-uniformity (PRNU) noise pattern, a powerful device fingerprint. Here, to address the image forgery localization…
Detection of video shot transition is a crucial pre-processing step in video analysis. Previous studies are restricted on detecting sudden content changes between frames through similarity measurement and multi-scale operations are widely…
Patch-Match is an efficient algorithm used for structural image editing and available as a tool on popular commercial photo-editing software. The tool allows users to insert or remove objects from photos using information from similar scene…
Indoor localization has many applications, such as commercial Location Based Services (LBS), robotic navigation, and assistive navigation for the blind. This paper formulates the indoor localization problem into a multimedia retrieving…
Videos captured by consumer cameras often exhibit temporal variations in color and tone that are caused by camera auto-adjustments like white-balance and exposure. When such videos are sub-sampled to play fast-forward, as in the…
Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…
The identification of source cameras from videos, though it is a highly relevant forensic analysis topic, has been studied much less than its counterpart that uses images. In this work we propose a method to identify the source camera of a…
This work details a highly efficient implementation of the 3D scale-invariant feature transform (SIFT) algorithm, for the purpose of machine learning from large sets of volumetric medical image data. The primary operations of the 3D SIFT…