Abstract | ||
---|---|---|
Significant progress has been made in terms of computational models of bottom-up visual attention (saliency). However, efficient ways of comparing these models for still images remain an open research question. The problem is even more challenging when dealing with videos and dynamic saliency. The paper proposes a framework for dynamic-saliency model evaluation, based on a new database of diverse videos for which eye-tracking data has been collected. In addition, we present evaluation results obtained for 4 state-of-the-art dynamic-saliency models, two of which have not been verified on eye-tracking data before. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-37431-9_45 | ACCV (3) |
Keywords | Field | DocType |
dynamic-saliency model evaluation,new database,eye-tracking data,efficient way,human attention,state-of-the-art dynamic-saliency model,computational model,comparative study,dynamic saliency,present evaluation result,bottom-up visual attention,diverse video,dynamic saliency model | Open research,Computer vision,Salience (neuroscience),Computer science,Visual attention,Computational model,Independent component analysis,Artificial intelligence,Visual saliency | Conference |
Citations | PageRank | References |
21 | 0.86 | 15 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicolas Riche | 1 | 184 | 9.75 |
Matei Mancas | 2 | 315 | 27.50 |
Dubravko Culibrk | 3 | 279 | 20.02 |
Crnojević, V. | 4 | 45 | 2.45 |
Bernard Gosselin | 5 | 198 | 12.88 |
Thierry Dutoit | 6 | 1006 | 123.84 |