| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| aws-d:citius_video_awsd [2016/10/13 16:41] – jorge.suarez | aws-d:citius_video_awsd [2018/05/01 22:47] (actual) – [INDEX] victor.leboran |
|---|
| ======= INDEX ======= | ======= INDEX ======= |
| * //[[:aws-d:citius_video_database|CITIUS-Dataset]]// | * //[[:aws-d:citius_video_database|CITIUS-Dataset]]// |
| | * //[[:aws-d:extended_video_database|Extended-DB Dataset]]// |
| * //[[:aws-d:citius_video_AWSD|AWS-D Matlab Code]]// | * //[[:aws-d:citius_video_AWSD|AWS-D Matlab Code]]// |
| * //[[:aws-d:citius_video_benchmark_localDB|AWS-D results - CITIUS VDB]]// | * //[[:aws-d:citius_video_benchmark_localDB|AWS-D results - CITIUS VDB]]// |
| |
| ======= AWS-D Saliency Model ======= | ======= AWS-D Saliency Model ======= |
| A manuscript with the complete description of the model and its results has been published in the IEEE T-PAMI journal ([[inv:downloadable_results:citius_video_database#bib_reference|info]]). If you are interested in obtaining our Matlab [[https://wiki.citius.usc.es/_media/inv:downloadable_results:aws-d.zip| p-code]] please contact us at [[http://citius.usc.es/equipo/investigadores-en-formacion/victor.leboran | victor.leboran@usc.es]]. Kindly indicate your university/industry affiliation and a brief description of how you plan to use the code. | A manuscript with the complete description of the model and its results has been published in the IEEE T-PAMI journal ([[:aws-d:citius_video_database#bib_reference|info]]). If you are interested in obtaining our Matlab [[https://wiki.citius.usc.es/_media/:inv:downloadable_results:aws-d.zip| p-code]] please contact us at [[http://citius.usc.es/equipo/investigadores-en-formacion/victor.leboran | victor.leboran@usc.es]]. Kindly indicate your university/industry affiliation and a brief description of how you plan to use the code. |
| {{ :talk:inv:downloadable_results:awsd-model.jpg?600 }} | {{ :aws-d:awsd-model.jpg?600 }} |
| ===== Software Usage (AWS-D model evaluation) ====== | ===== Software Usage (AWS-D model evaluation) ====== |
| To make a test with this model it's only necessary to use one video as input. The AWS-D model returns a video output with the same resolution as the input video. | To make a test with this model it's only necessary to use one video as input. The AWS-D model returns a video output with the same resolution as the input video. |
| Next figure shows the AWSD model aplied to the //rcd-surf2// CITIUS-VDB video (left), the saliency overimposed to the original video in falsecolor (center) and the saliency map (right) as a grayscale image, where white pixels represent most probable fixation positions and black pixels represent less likely fixation positions. | Next figure shows the AWSD model aplied to the //rcd-surf2// CITIUS-VDB video (left), the saliency overimposed to the original video in falsecolor (center) and the saliency map (right) as a grayscale image, where white pixels represent most probable fixation positions and black pixels represent less likely fixation positions. |
| | ^ Original Video ^ Superimposed map ^ Saliency map | | | | ^ Original Video ^ Superimposed map ^ Saliency map | | |
| | ::: | {{:talk:inv:downloadable_results:rcd_surf_2_120x160.gif|Original Video}} | {{:talk:inv:downloadable_results:rcd_surf_2_120x160_sm_vid_map.gif|Video with Saliency Map}} | {{:talk:inv:downloadable_results:rcd_surf_2_120x160_sm_awsd.gif|Saliency Map}} | ::: | | | ::: | {{:aws-d:rcd_surf_2_120x160.gif|Original Video}} | {{:aws-d:rcd_surf_2_120x160_sm_vid_map.gif|Video with Saliency Map}} | {{:aws-d:rcd_surf_2_120x160_sm_awsd.gif|Saliency Map}} | ::: | |
| ======= Comparison with fixations database ======= | ======= Comparison with fixations database ======= |
| We have prepared a database (CITIUS-VDB) with a collection of eye movements from 22 human observers (aged 11-43 years) as they freely viewing 72 videos. Recorded using a SMI RED remote eye tracker (120Hz sampling rate and average calibration error less than 0.5 degrees), and to be made available to the vision research community. The database, along with MATLAB functions for its use, will be download freely [[https://wiki.citius.usc.es/inv:downloadable_results:citius_video_database#thumbnails_of_videos|here]], and will be used without restriction for educational and research purposes, providing that our paper “Dynamic Whitening Saliency” submitted to the IEEE Transactions on Pattern Analysis and Machine Intelligence is cited in any published work. | We have prepared a database (CITIUS-VDB) with a collection of eye movements from 22 human observers (aged 11-43 years) as they freely viewing 72 videos. Recorded using a SMI RED remote eye tracker (120Hz sampling rate and average calibration error less than 0.5 degrees), and to be made available to the vision research community. The database, along with MATLAB functions for its use, will be download freely [[https://wiki.citius.usc.es/inv:downloadable_results:citius_video_database#thumbnails_of_videos|here]], and will be used without restriction for educational and research purposes, providing that our paper “Dynamic Whitening Saliency” submitted to the IEEE Transactions on Pattern Analysis and Machine Intelligence is cited in any published work. |