4 papers
Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusions
Zhixuan Li, Yujia Liu, Chen Hui +3
Amodal segmentation targets to predict complete object masks, covering both visible and occluded regions. This task poses significant challenges due to complex occlusions and extre…
Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation
Zhixuan Li, Yujia Liu, Chen Hui +1
Amodal segmentation aims to recover complete object shapes, including occluded regions with no visual appearance, whereas conventional segmentation focuses solely on visible areas.…
BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting
Zhixuan Li, Naipeng Chen, Seonghwa Choi +2
Time-series forecasting is crucial for numerous real-world applications including weather prediction and financial market modeling. While temporal-domain methods remain prevalent,…
Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA
Zhixuan Li, Hyunse Yoon, Sanghoon Lee +1
Amodal segmentation aims to infer the complete shape of occluded objects, even when the occluded region's appearance is unavailable. However, current amodal segmentation methods la…