8 papers
Seek to Segment: Active Perception for Panoramic Referring Segmentation
Song Tang, Shuming Hu, Xincheng Shuai +2
Existing referring segmentation models passively process static images captured from fixed perspectives, limiting their applicability in Embodied AI, where agents must perform acti…
Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation
Jinyu Liu, Xincheng Shuai, Henghui Ding +1
Unified multimodal models capable of both understanding and generation have achieved remarkable strides. However, despite their unified designs, existing evaluations typically asse…
ROSE: Retrieval-Oriented Segmentation Enhancement
Song Tang, Guangquan Jie, Henghui Ding +1
Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inability to incorporate u…
GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation
Henghui Ding, Chang Liu, Shuting He +2
Referring Expression Segmentation (RES) and Comprehension (REC) respectively segment and detect the object described by an expression, while Referring Expression Generation (REG) g…
MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
Henghui Ding, Chang Liu, Shuting He +4
This paper proposes a large-scale multi-modal dataset for referring motion expression video segmentation, focusing on segmenting and tracking target objects in videos based on lang…
MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes
Henghui Ding, Kaining Ying, Chang Liu +5
Video object segmentation (VOS) aims to segment specified target objects throughout a video. Although state-of-the-art methods have achieved impressive performance (e.g., 90+% J&F)…