File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2013.401
- Scopus: eid_2-s2.0-84898807239
- WOS: WOS:000351830500404
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Semantically-based human scanpath estimation with HMMs
Title | Semantically-based human scanpath estimation with HMMs |
---|---|
Authors | |
Keywords | Attention Gaze shift Hidden Markov Model Levy flight Saliency |
Issue Date | 2013 |
Citation | Proceedings of the IEEE International Conference on Computer Vision, 2013, p. 3232-3239 How to Cite? |
Abstract | We present a method for estimating human scan paths, which are sequences of gaze shifts that follow visual attention over an image. In this work, scan paths are modeled based on three principal factors that influence human attention, namely low-level feature saliency, spatial position, and semantic content. Low-level feature saliency is formulated as transition probabilities between different image regions based on feature differences. The effect of spatial position on gaze shifts is modeled as a Levy flight with the shifts following a 2D Cauchy distribution. To account for semantic content, we propose to use a Hidden Markov Model (HMM) with a Bag-of-Visual-Words descriptor of image regions. An HMM is well-suited for this purpose in that 1) the hidden states, obtained by unsupervised learning, can represent latent semantic concepts, 2) the prior distribution of the hidden states describes visual attraction to the semantic concepts, and 3) the transition probabilities represent human gaze shift patterns. The proposed method is applied to task-driven viewing processes. Experiments and analysis performed on human eye gaze data verify the effectiveness of this method. © 2013 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/321579 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Huiying | - |
dc.contributor.author | Xu, Dong | - |
dc.contributor.author | Huang, Qingming | - |
dc.contributor.author | Li, Wen | - |
dc.contributor.author | Xu, Min | - |
dc.contributor.author | Lin, Stephen | - |
dc.date.accessioned | 2022-11-03T02:20:00Z | - |
dc.date.available | 2022-11-03T02:20:00Z | - |
dc.date.issued | 2013 | - |
dc.identifier.citation | Proceedings of the IEEE International Conference on Computer Vision, 2013, p. 3232-3239 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321579 | - |
dc.description.abstract | We present a method for estimating human scan paths, which are sequences of gaze shifts that follow visual attention over an image. In this work, scan paths are modeled based on three principal factors that influence human attention, namely low-level feature saliency, spatial position, and semantic content. Low-level feature saliency is formulated as transition probabilities between different image regions based on feature differences. The effect of spatial position on gaze shifts is modeled as a Levy flight with the shifts following a 2D Cauchy distribution. To account for semantic content, we propose to use a Hidden Markov Model (HMM) with a Bag-of-Visual-Words descriptor of image regions. An HMM is well-suited for this purpose in that 1) the hidden states, obtained by unsupervised learning, can represent latent semantic concepts, 2) the prior distribution of the hidden states describes visual attraction to the semantic concepts, and 3) the transition probabilities represent human gaze shift patterns. The proposed method is applied to task-driven viewing processes. Experiments and analysis performed on human eye gaze data verify the effectiveness of this method. © 2013 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE International Conference on Computer Vision | - |
dc.subject | Attention | - |
dc.subject | Gaze shift | - |
dc.subject | Hidden Markov Model | - |
dc.subject | Levy flight | - |
dc.subject | Saliency | - |
dc.title | Semantically-based human scanpath estimation with HMMs | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICCV.2013.401 | - |
dc.identifier.scopus | eid_2-s2.0-84898807239 | - |
dc.identifier.spage | 3232 | - |
dc.identifier.epage | 3239 | - |
dc.identifier.isi | WOS:000351830500404 | - |