Seek to Segment: Active Perception for Panoramic Referring Segmentation
Existing referring segmentation models passively process static images captured from fixed perspectives, limiting their applicability in Embodied AI, where agents must perform active perception in the continuous 360$^\circ$ environments. To bridge this gap, we introduce a novel task: Active Panoramic Referring Segmentation (APRS). In this setting, an agent is required to adjust its viewing direction ($Δθ, Δφ$) to explore the 360$^\circ$ environment, seeking the object specified by a user instruction for segmentation. To tackle this challenging task, we propose PanoSeeker, a memory-augmented ag
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%VioletVision-3B →
- PossiblePossibly related (embedding) · 48%Into the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning →
- PossiblePossibly related (embedding) · 46%digiteinfotech/kairon →
- LinkedLinked via arxiv author · 85%Song Tang →
“Seek to Segment: Active Perception for Panoramic Referring Segmentation”
- LinkedLinked via arxiv author · 85%Shuming Hu →
“Seek to Segment: Active Perception for Panoramic Referring Segmentation”
- LinkedLinked via arxiv author · 85%Xincheng Shuai →
“Seek to Segment: Active Perception for Panoramic Referring Segmentation”
- LinkedLinked via arxiv author · 85%Henghui Ding →
“Seek to Segment: Active Perception for Panoramic Referring Segmentation”
- LinkedLinked via arxiv author · 85%Yu-Gang Jiang →
“Seek to Segment: Active Perception for Panoramic Referring Segmentation”