Web archivists have a difficult time gathering web video that are, more often than not served with non-standard tools and protocols. This paper offers a survey of the state of the art in this domain. Based on an experience of several years gathering web video content, we present detailed examples to help understand the issues and solution to capture web video content. We also present a architec...

Speaker diarization currently focuses on using audio features to partition an audio stream into speaker homogeneous speech regions, in other words to determine “who spoke when”. Recent speaker diarization corpora contains video recordings in addition to the commonly used audio. Thus, we investigated the benefits of incorporating video features, namely histograms of weighted oriented optical flo...

We describe FreeCam a system capable of generating live free-viewpoint video by simulating the output of a virtual camera moving through a dynamic scene. The FreeCam sensing hardware consists of a small number of static color video cameras and state-of-the-art Kinect depth sensors, and the FreeCam software uses a number of advanced GPU processing and rendering techniques to seamlessly merge the...

Video games have existed for over half a century. Visual attention and eye movement studies, as well as techniques to analyze these movements, have occupied the attention of researchers since late 19 century. This paper presents a review of the state of the art on how video games and visual attention relate as well as how eye tracking has been used to the benefit of video games, both as a form ...

As speech recognizers become more robust, they are popularly accepted as an essential component of human-computer interaction. State-ofthe-art speaker-independent speech recognizers exist with word recognition error rates below 10%. To achieve even higher and robust recognition performance, multi-modal speech recognition techniques that combine video and audio information call be used. Speech r...

Objective video quality metrics are designed to estimate the quality of experience of the end user. However, these objective metrics are usually validated with video streams degraded under common distortion types. In the presented work, we analyze the performance of published and known full-reference and noreference quality metrics in estimating the perceived quality of adaptive bit-rate video ...

This paper summarizes our recent research works on semantic video search. Our solution to this exciting topic is grounded on concept-based video search, which attempts to narrow the semantic gap by first indexing the video content with a large number of pre-trained semantic concepts, and then employing these concepts to respond user’s queries (query-by-concept). We developed novel and effective...

Current state-of-the art object detection and recognition algorithms mainly use supervised training, and most benchmark datasets contain only static images. In this work we study feature learning in the context of temporally coherent video data. We focus on training convolutional features on unlabeled video data, using only the assumption that adjacent video frames contain semantically similar ...

In this paper we present a variational, spatiotemporal video super resolution scheme that produces not just one but n high resolution video frames from an n frame low resolution video sequence. We use a generic prior and the output is artifact-free, sharp and superior in quality to state of the art home cinema video processors. Unlike many other super resolution schemes, ours does not limit its...