Multimedia Analysis
Hi! You've probably arrived here from the link on one of our papers. Here you will find a short collection of multimedia data related projects and publications. Click on one of the bookmarks for fast navigation to the publications page where you will find links to all information related to the paper.
Semantic Video Understanding
[CVPR2016]
[CVPR2015]
[CVPR2014]
[ICMR2014]
Face and Person Identification, Retrieval
[ICMR2015]
[FG2015]
[AVSS2014]
[CVPR2013]
[CVPR2012]
or browse below to know about the status of code and data release.
Code and Data set downloads
Semantic Video Understanding
- , CVPR 2016
- MovieQA: Story Understanding Benchmark data and baselines code
- CVPR 2015
- Alignment between novels and their TV series or film adaptations
- , CVPR 2014
- StoryGraphs: Codes to generate the visualization by loading all necessary data now available on Github (currently supports BBT, BUFFY)
- ICMR 2014
- Plot synopsis: alignment annotations on 22 episodes of BUFFY
Person Identification
- ICMR 2015
- Face tracks on all eight movies of the Harry Potter series to study effect of aging on id. Features (9GB+) can also be downloaded.
- FG 2015
- Improved weak labeling for person identification in TV series. Code available on Github
- AVSS 2014
- Large scale id: face tracks for season 5 all 22 episodes of BUFFY. Download single MAT file containing tracks for all episodes
- CVPR 2013
- Semi-supervised learning: face tracks on 6 episodes of BBT and BUFFY.
- , CVPR 2012
- PersonID: Preliminary helper code, face tracks, person tracks, video events on 6 episodes of BBT
Face Tracking
- CVPR 2013
- Download manually annotated face track bounding boxes for 6 episodes each of BBT and BUFFY which can be used for face tracking evaluation.