Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224903670> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4224903670 abstract "Human visual attention is a complex phenomenon that has been studied for decades. Within it, the particular problem of scanpath prediction poses a challenge, particularly due to the inter- and intra-observer variability, among other reasons. Besides, most existing approaches to scanpath prediction have focused on optimizing the prediction of a gaze point given the previous ones. In this work, we present a probabilistic time-evolving approach to scanpath prediction, based on Bayesian deep learning. We optimize our model using a novel spatio-temporal loss function based on a combination of Kullback-Leibler divergence and dynamic time warping, jointly considering the spatial and temporal dimensions of scanpaths. Our scanpath prediction framework yields results that outperform those of current state-of-the-art approaches, and are almost on par with the human baseline, suggesting that our model is able to generate scanpaths whose behavior closely resembles those of the real ones." @default.
- W4224903670 created "2022-04-27" @default.
- W4224903670 creator A5001550110 @default.
- W4224903670 creator A5002799290 @default.
- W4224903670 creator A5058811614 @default.
- W4224903670 date "2022-04-20" @default.
- W4224903670 modified "2023-10-16" @default.
- W4224903670 title "A Probabilistic Time-Evolving Approach to Scanpath Prediction" @default.
- W4224903670 doi "https://doi.org/10.48550/arxiv.2204.09404" @default.
- W4224903670 hasPublicationYear "2022" @default.
- W4224903670 type Work @default.
- W4224903670 citedByCount "0" @default.
- W4224903670 crossrefType "posted-content" @default.
- W4224903670 hasAuthorship W4224903670A5001550110 @default.
- W4224903670 hasAuthorship W4224903670A5002799290 @default.
- W4224903670 hasAuthorship W4224903670A5058811614 @default.
- W4224903670 hasBestOaLocation W42249036701 @default.
- W4224903670 hasConcept C107673813 @default.
- W4224903670 hasConcept C119857082 @default.
- W4224903670 hasConcept C138885662 @default.
- W4224903670 hasConcept C154945302 @default.
- W4224903670 hasConcept C171752962 @default.
- W4224903670 hasConcept C207390915 @default.
- W4224903670 hasConcept C41008148 @default.
- W4224903670 hasConcept C41895202 @default.
- W4224903670 hasConcept C49937458 @default.
- W4224903670 hasConcept C88516994 @default.
- W4224903670 hasConceptScore W4224903670C107673813 @default.
- W4224903670 hasConceptScore W4224903670C119857082 @default.
- W4224903670 hasConceptScore W4224903670C138885662 @default.
- W4224903670 hasConceptScore W4224903670C154945302 @default.
- W4224903670 hasConceptScore W4224903670C171752962 @default.
- W4224903670 hasConceptScore W4224903670C207390915 @default.
- W4224903670 hasConceptScore W4224903670C41008148 @default.
- W4224903670 hasConceptScore W4224903670C41895202 @default.
- W4224903670 hasConceptScore W4224903670C49937458 @default.
- W4224903670 hasConceptScore W4224903670C88516994 @default.
- W4224903670 hasLocation W42249036701 @default.
- W4224903670 hasOpenAccess W4224903670 @default.
- W4224903670 hasPrimaryLocation W42249036701 @default.
- W4224903670 hasRelatedWork W2043695334 @default.
- W4224903670 hasRelatedWork W2091295168 @default.
- W4224903670 hasRelatedWork W2123736238 @default.
- W4224903670 hasRelatedWork W2223779168 @default.
- W4224903670 hasRelatedWork W2535170036 @default.
- W4224903670 hasRelatedWork W2787886158 @default.
- W4224903670 hasRelatedWork W2798792107 @default.
- W4224903670 hasRelatedWork W3118903907 @default.
- W4224903670 hasRelatedWork W3204552159 @default.
- W4224903670 hasRelatedWork W952002620 @default.
- W4224903670 isParatext "false" @default.
- W4224903670 isRetracted "false" @default.
- W4224903670 workType "article" @default.