Free-hand sketch grouping for video retrieval

Collomosse, John; McNeill, Graham; Watts, Leon

doi:10.1109/icpr.2008.4761466

Cited by 22 publications

(40 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Strokes indicating the motion direction are drawn in a different ink which is used to depict the object. Simple arrow pictograms may be recognised in the sketch using [24] and the shaft of the arrow isolated. The shaft sampled at regular intervals to yield a sequence of vectors of constant length, which represent the motion of the according segment.…”

Section: Sketch Parsing and Descriptionmentioning

confidence: 99%

Markov random fields for sketch based video retrieval

James

Wang

et al. 2013

Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

We describe a new system for searching video databases using free-hand sketched queries. Our query sketches depict both object appearance and motion, and are annotated with keywords that indicate the semantic category of each object. We parse space-time volumes from video to form graph representation, which we match to sketches under a Markov Random Field (MRF) optimization. The MRF energy function is used to rank videos for relevance and contains unary, pairwise and higher-order potentials that reflect the colour, shape, motion and type of sketched objects. We evaluate performance over a dataset of 500 sports footage clips.

show abstract

Section: Sketch Parsing and Descriptionmentioning

confidence: 99%

Markov random fields for sketch based video retrieval

James

Wang

et al. 2013

Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…For example, motion cues have direction but do not reliably depict the magnitude of motion [5] (yet this information is required by [2]). This ambiguity forced us to introduce assumptions into our model; we assume the sketch canvas to approximate a mosaic spanning all frames, and that sketched motion extends across this.…”

Section: Resultsmentioning

confidence: 99%

“…Our two-step sketch parsing process [5] comprises: HMM based recognition of common pictogram objects (stick-men, arrows, streak-lines) followed by grouping of remaining non-pictogram strokes into objects using graphcut. From each non-motion cue object grouped by [5], we Figure 1.…”

Section: Descriptions Of Sketched Objectsmentioning

confidence: 99%

See 1 more Smart Citation

Reverse storyboarding for video retrieval

McNeill

Collomosse

2007

IET 4th European Conference on Visual Media Production (CVMP 2007)

Self Cite

View full text Add to dashboard Cite

We present a novel Content Based Video Retrieval (CBVR) system, driven by free-hand sketch queries depicting both objects and their movement (via dynamic cues; streak-lines and arrows). Our main contribution is a probabilistic model of video clips (based on Linear Dynamical Systems), leading to an algorithm for matching descriptions of sketched objects to video. We demonstrate our model fitting to clips under static and moving camera conditions, exhibiting linear and oscillatory motion. We evaluate retrieval on two real video data sets, and on a video data set exhibiting controlled variation in shape, color, motion and clutter.

show abstract

“…To alleviate the user's effort, some systems follow an interactive setup [17], where the user performs a keyword-based search, selects relevant visual examples from retrieved results, and launches image-based searches in an iterative fashion. Other approaches allow the user to provide a sketch as a visual example, which is analysed with specialised algorithms to let low-level feature search over the video collection [6]. These two approaches, however, still require more effort to the user than the keyword-based paradigm.…”

Section: Introductionmentioning

confidence: 99%

Exploiting semantics on external resources to gather visual examples for video retrieval

Vallet

Cantador

Jose

2012

Int J Multimed Info Retr

View full text Add to dashboard Cite

With the huge and ever rising amount of video content available on the Web, there is a need to facilitate video retrieval functionalities on very large collections. Most of the current Web video retrieval systems rely on manual textual annotations to provide keyword-based search interfaces. These systems have to face the problems that users are often reticent to provide annotations, and that the quality of such annotations is questionable in many cases. An alternative commonly used approach is to ask the user for an image example, and exploit the low-level features of the image to find video content whose keyframes are similar to the image. In this case, the main limitation is the so-called semantic gap, which consists of the fact that low-level image features often do not match with the real semantics of the videos. Moreover, this approach may be a burden to the user, as it requires finding and providing the system with relevant visual examples. Aiming to address this limitation, in this paper, we present a hybrid video retrieval technique that automatically obtains visual examples by performing textual searches on external knowledge sources, such as DBpedia, Flickr and Google Images, which have different coverage and structure characteristics. Our approach exploits the semantics underlying the above knowledge sources to address the semantic gap problem. We have conducted evaluations to assess the quality of visual examples retrieved from the above external knowledge sources.

show abstract

Free-hand sketch grouping for video retrieval

Cited by 22 publications

References 12 publications

Markov random fields for sketch based video retrieval

Markov random fields for sketch based video retrieval

Reverse storyboarding for video retrieval

Exploiting semantics on external resources to gather visual examples for video retrieval

Contact Info

Product

Resources

About