WP-L.B.2

SYNCHRONIZED AUDIO-VISUAL FRAMES WITH FRACTIONAL POSITIONAL ENCODING FOR TRANSFORMERS IN VIDEO-TO-TEXT TRANSLATION

Philipp Harzig, Moritz Einfalt, Rainer Lienhart, University of Augsburg, Germany
Session:
Machine Learning for 3D Processing
Lecture
Track:
Applications of Machine Learning
Location:
Room B
Presentation Time:
Wed, 19 Oct, 22:45 - 23:00 China Standard Time (UTC +8)
Wed, 19 Oct, 16:45 - 17:00 Central European Time (UTC +1)
Wed, 19 Oct, 14:45 - 15:00 UTC
Wed, 19 Oct, 10:45 - 11:00 Eastern Time (UTC -5)
Session Co-Chairs:
Yoshinari Kameda, University of Tsukuba and Changjae Oh, Queen Mary University of London
Presentation
Discussion
Resources
No resources available.
Session WP-L.B
WP-L.B.1: BOUNDING BOX DISPARITY: 3D METRICS FOR OBJECT DETECTION WITH FULL DEGREE OF FREEDOM
Michael G. Adam, Martin Piccolrovazzi, Sebastian Eger, Eckehard Steinbach, Technical University of Munich, Germany
WP-L.B.2: SYNCHRONIZED AUDIO-VISUAL FRAMES WITH FRACTIONAL POSITIONAL ENCODING FOR TRANSFORMERS IN VIDEO-TO-TEXT TRANSLATION
Philipp Harzig, Moritz Einfalt, Rainer Lienhart, University of Augsburg, Germany
WP-L.B.3: CLUSTER-BASED 3D KEYPOINT DETECTION FOR CATEGORY-AGNOSTIC 6D POSE TRACKING
Long Tian, Andrea Cavallaro, Changjae Oh, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland
WP-L.B.4: DEEP WEIGHTED CONSENSUS DENSE CORRESPONDENCE CONFIDENCE MAPS FOR 3D SHAPE REGISTRATION
Dvir Ginzburg, Dan Raviv, Tel Aviv University, Israel
WP-L.B.5: LB-NERF: LIGHT BENDING NEURAL RADIANCE FIELDS FOR TRANSPARENT MEDIUM
Taku Fujitomi, University of Tsukuba / National Institute of Advanced Industrial Science and Technology, Japan; Ken Sakurada, Ryuhei Hamaguchi, National Institute of Advanced Industrial Science and Technology, Japan; Hidehiko Shishido, Yoshinari Kameda, University of Tsukuba, Japan; Masaki Onishi, Institute of Advanced Industrial Science and Technology, Japan