• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations

J.P.: Annotated free-hand sketches for video retrieval using object semantics and motion (0)

by R Hu, S James, Collomosse
Venue:In: MMM
Add To MetaCart

Tools

Sorted by:
Results 1 - 2 of 2

Markov Random Fields for Sketch based Video Retrieval

by Rui Hu, Stuart James, Tinghuai Wang, John Collomosse
"... We describe a new system for searching video databases us-ing free-hand sketched queries. Our query sketches depict both object appearance and motion, and are annotated with ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
We describe a new system for searching video databases us-ing free-hand sketched queries. Our query sketches depict both object appearance and motion, and are annotated with
(Show Context)

Citation Context

...h are clustered to form a set of space-time tokens. A Viterbi-like process matches the space-time graph of tokens to the colour and motion description of the query sketch. The approach is extended in =-=[18]-=- using a more robust motion clustering algorithm, where semantic information is also considered. However, as with early SBVR [15], retrieval performance is strongly dependent on the accuracy of the vi...

A Performance Evaluation of Gradient Field HOG Descriptor for Sketch Based Image Retrieval

by Rui Hu A, John Collomosse A
"... We present an image retrieval system for the interactive search of photo collections using free-hand sketches depicting shape. We describe Gradient Field HOG (GF-HOG); an adapted form of the HOG descriptor suitable for sketch based image retrieval (SBIR). We incorporate GF-HOG into a Bag of Visual W ..."
Abstract - Add to MetaCart
We present an image retrieval system for the interactive search of photo collections using free-hand sketches depicting shape. We describe Gradient Field HOG (GF-HOG); an adapted form of the HOG descriptor suitable for sketch based image retrieval (SBIR). We incorporate GF-HOG into a Bag of Visual Words (BoVW) retrieval framework, and demonstrate how this combination may be harnessed both for robust SBIR, and for localizing sketched objects within an image. We evaluate over a large Flickr sourced dataset comprising 33 shape categories, using queries from 10 non-expert sketchers. We compare GF-HOG against state-of-the-art descriptors with common distance measures and language models for image retrieval, and explore how affine deformation of the sketch impacts search performance. GF-HOG is shown to consistently outperform retrieval versus SIFT, multi-resolution HOG, Self Similarity, Shape Context and Structure Tensor. Further, we incorporate semantic keywords in to our GF-HOG system to enable the use of annotated sketches for image search. A novel graph-based measure of semantic similarity is proposed and two applications explored: semantic sketch based image retrieval and a semantic photo montage.
(Show Context)

Citation Context

...the asymmetric score measure of [42] so that the similarity between two tags considers not only the explicit co-occurrence but also the implicit co-occurrence of keywords. Note that our previous work =-=[49]-=- incorporating semantics for sketch based video retrieval. Annotated sketches are used as queries for video retrieval. Videos are first segmented into spatio-temporal volumes and a histogram distribut...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University