9 papers
SAMOT: State-Aware Step Modulation and Optimal Transport Matching for Audio-Visual Instance Segmentation
Kai Peng, Yunzhe Shen, Miao Zhang +5
Audio-Visual Instance Segmentation (AVIS) aims to simultaneously classify, segment, and track sounding objects within video sequences. Unlike Audio-Visual Semantic Segmentation (AV…
Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation
Leiye Liu, Miao Zhang, Jiahong Jiang +7
Audio-visual instance segmentation (AVIS) requires accurately identifying and tracking individual sounding objects with pixel-level masks. Existing methods struggle to match overla…
AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis
Jialong Zhong, Tingwei Liu, Baokun Yue +7
Multimodal survival analysis utilizing whole slide images (WSIs) and genomic profiles is fundamental for cancer prognosis. Recently, state-space models like Mamba have emerged as p…
ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning
Yuan Zhao, Youwei Pang, Jiaming Zuo +10
Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the notion of a concept remains…
UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings
Bo Zhao, Maosheng Pang, Chen Zhang +3
Existing works typically focus on presentation generation under isolated input settings, whereas real-world use cases span diverse scenarios, including vague user prompts, long doc…
SAM3-I: Segment Anything with Instructions
Jingjing Li, Yue Feng, Yuchen Guo +10
Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instances associated with a given conce…