Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360 ^∘ Videos

Omnidirectional videos (ODVs) are redefining viewer experiences in virtual reality (VR) by offering an unprecedented full field-of-view (FOV). This study extends the domain of saliency prediction to 360^\circ ∘ environments, addressing the complexities of spherical distortion and the integration of...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence 2026-01, Vol.48 (1), p.329-345
Main Authors:	Cokelek, Mert, Ozsoy, Halit, Imamoglu, Nevrez, Ozcinar, Cagri, Ayhan, Inci, Erdem, Erkut, Erdem, Aykut
Format:	Article
Language:	English
Subjects:	360<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX"> ^\circ</tex-math> <mml:math> <mml:msup> <mml:mrow/> <mml:mo>∘</mml:mo> </mml:msup> </mml:math> <inline-graphic xlink:href="erdem-ieq7-3604091.gif" xlink:type="simple"/> </inline-formula> </named-content> videos adapter fine-tuning Ambisonics Audio-visual saliency prediction Convolution Distortion Faces MONOS devices Predictive models Spatial audio Transformers Videos vision transformers Visualization
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!