Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Yun, Heeseung"'
Autor:
Yun, Heeseung, Gao, Ruohan, Ananthabhotla, Ishwarya, Kumar, Anurag, Donley, Jacob, Li, Chao, Kim, Gunhee, Ithapu, Vamsi Krishna, Murdock, Calvin
Egocentric videos provide comprehensive contexts for user and scene understanding, spanning multisensory perception to behavioral interaction. We propose Spherical World-Locking (SWL) as a general framework for egocentric scene representation, which
Externí odkaz:
http://arxiv.org/abs/2408.05364
Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge distillation. In t
Externí odkaz:
http://arxiv.org/abs/2309.11081
360$^\circ$ video saliency detection is one of the challenging benchmarks for 360$^\circ$ video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360$^\circ$ videos, and capture-worthy viewpoint
Externí odkaz:
http://arxiv.org/abs/2209.08956
Autor:
Yu, Youngjae, Chung, Jiwan, Yun, Heeseung, Hessel, Jack, Park, JaeSung, Lu, Ximing, Ammanabrolu, Prithviraj, Zellers, Rowan, Bras, Ronan Le, Kim, Gunhee, Choi, Yejin
Large language models readily adapt to novel settings, even without task-specific training data. Can their zero-shot capacity be extended to multimodal inputs? In this work, we propose ESPER which extends language-only zero-shot models to unseen mult
Externí odkaz:
http://arxiv.org/abs/2205.12630
360$^\circ$ videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond pre-determined normal field of views and displays distinctive spatial relations on a sphere. However, previous benchmark tasks for panorami
Externí odkaz:
http://arxiv.org/abs/2110.05122
We develop a system which generates summaries from seniors' indoor-activity videos captured by a social robot to help remote family members know their seniors' daily activities at home. Unlike the traditional video summarization datasets, indoor vide
Externí odkaz:
http://arxiv.org/abs/1901.10713
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.