Using Hand Gestures for Specifying Motion Queries in Sketch-Based Video Retrieval

Kabary, Ihab Al; Schuldt, Heiko

doi:10.1007/978-3-319-06028-6_84

Cited by 4 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example query searches for video snippets that start somewhere in the midfield, with a path to the left side of the field, followed by a pass into the penalty box and ending with a goal or a shot on or off target. In our previous work in SportSense [16,17,18], we developed an event cascade query type in which the user sketches the areas in which each of the events happens in a chronological order. In this pipeline query, with each sketch, the results tend to narrow down until the desired results are reached as shown in Figures 1(a) to 1(c).…”

Section: Query Formulation and User Interactionmentioning

confidence: 99%

“…SportSense [16,17,18] is an approach to search in team sports videos on the basis of motion paths sketched by a user. However, from our previous work, we have discovered that searching for known items in the form of motion queries relies to a great extent on the memory of users and their ability to project a 3D memory on a 2D screen in the form of a query sketch, and this affects the accuracy of the results and the ease of use of the system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing sketch-based sport video retrieval by suggesting relevant motion paths

Kabary

Schuldt

2014

Proceedings of the 37th International ACM SIGIR Conference on Research &Amp; Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

Searching for scenes in team sport videos is a task that recurs very often in game analysis and other related activities performed by coaches. In most cases, queries are formulated on the basis of specific motion characteristics the user remembers from the video. Providing sketching interfaces for graphically specifying query input is thus a very natural user interaction for a retrieval application. However, the quality of the query (the sketch) heavily depends on the memory of the user and her ability to accurately formulate the intended search query by transforming this 3D memory of the known item(s) into a 2D sketch query. In this paper, we present an auto-suggest search feature that harnesses spatiotemporal data of team sport videos to suggest potential directions containing relevant data during the formulation of a sketch-based motion query. Users can intuitively select the direction of the desired motion query on-the-fly using the displayed visual clues, thus relaxing the need for relying heavily on memory to formulate the query. At the same time, this significantly enhances the accuracy of the results and the speed at which they appear. A first evaluation has shown the effectiveness and efficiency of our approach.

show abstract

Section: Query Formulation and User Interactionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing sketch-based sport video retrieval by suggesting relevant motion paths

Kabary

Schuldt

2014

Proceedings of the 37th International ACM SIGIR Conference on Research &Amp; Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each pose keeps the 3D coordinates of important skeleton joints in a specific time moment. Effective and efficient processing of such spatio-temporal data is very desirable in many application domains, ranging from computer animation, through sports and medicine, to security [5,7,9].…”

Section: Introductionmentioning

confidence: 99%

Motion Words: A Text-Like Representation of 3D Skeleton Sequences

Sedmidubský

Budikova

Dohnal

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

There is a growing amount of human motion data captured as a continuous 3D skeleton sequence without any information about its semantic partitioning. To make such unsegmented and unlabeled data efficiently accessible, we propose to transform them into a text-like representation and employ well-known text retrieval models. Specifically, we partition each motion synthetically into a sequence of short segments and quantize the segments into motion words, i.e. compact features with similar characteristics as words in text documents. We introduce several quantization techniques for building motion-word vocabularies and propose application-independent criteria for assessing the vocabulary quality. We verify these criteria on two real-life application scenarios.

show abstract

Scalable Sketch-Based Sport Video Retrieval in the Cloud

Kabary

Schuldt

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Using Hand Gestures for Specifying Motion Queries in Sketch-Based Video Retrieval

Cited by 4 publications

References 1 publication

Enhancing sketch-based sport video retrieval by suggesting relevant motion paths

Enhancing sketch-based sport video retrieval by suggesting relevant motion paths

Motion Words: A Text-Like Representation of 3D Skeleton Sequences

Scalable Sketch-Based Sport Video Retrieval in the Cloud

Contact Info

Product

Resources

About