5 papers · 1 filter
ViewBridge: Curriculum Knowledge Distillation for Activity View-Invariance Under Extreme Viewpoint Changes
Arjun Somayazulu, Efi Mavroudi, Changan Chen +2
Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with in-the-wild videos that exhibit…
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
Zihui Xue, Mi Luo, Changan Chen +1
We study the problem of precisely swapping objects in videos, with a focus on those interacted with by hands, given one user-provided reference object image. Despite the great adva…
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman, Andrew Westbury, Lorenzo Torresani +98
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric…
Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos
Changan Chen, Puyuan Peng, Ami Baid +4
Generating realistic audio for human actions is important for many applications, such as creating sound effects for films or virtual reality games. Existing approaches implicitly a…
ActiveRIR: Active Audio-Visual Exploration for Acoustic Environment Modeling
Arjun Somayazulu, Sagnik Majumder, Changan Chen +1
An environment acoustic model represents how sound is transformed by the physical characteristics of an indoor environment, for any given source/receiver location. Traditional meth…