2 papers
cs.CV2025
Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives
Jiaxin Li, Hongxing Wang, Jiawei Tan +2
Understanding 3D object shapes necessitates shape representation by object parts abstracted from results of instance and semantic segmentation. Promising shape representations enab…
cs.CV2024
Modality-Aware Shot Relating and Comparing for Video Scene Detection
Jiawei Tan, Hongxing Wang, Kang Dang +2
Video scene detection involves assessing whether each shot and its surroundings belong to the same scene. Achieving this requires meticulously correlating multi-modal cues, $\it{e.…