Newest papers

Moving Regions, Not Moving Objects: Segmenting What Actually Moves under Camera Motion

Wenhua Jin, Tiancheng Chen, Sheng Tang, Jiahao Li, Yupeng Liu, Weiqi Zhang, Juntong Fang, Zesong Li · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31209 · open-access PDF

Japanese

Moving object segmentation is conventionally formulated at the sequence and object level, marking an entire instance as moving once it moves anywhere in a video. Recent instantaneous formulations distinguish moving from stationary intervals, but still generate masks at the object level through frozen segmentation foundation models. Because the mask is derived from an instance-level proposition, motion is typically attributed to the entire instance rather than localized to the regions that actually move. さらに、このような instance-level predictions can produce masks even when no part of the instance is attributed to the entire instance. また、このような instance-level predictions can produce masks even when there is no part of the instance.

Machine translation (Meta M2M100); the English original follows.

Abstract

Moving object segmentation is conventionally formulated at the sequence and object level, marking an entire instance as moving once it moves anywhere in a video. Recent instantaneous formulations distinguish moving from stationary intervals, but still generate masks at the object level through frozen segmentation foundation models. Because the mask is derived from an instance-level proposal, motion is typically attributed to the entire instance rather than localized to the regions that actually move. Moreover, such instance-level predictions can produce masks even when no part of the instance

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange