5 papers
VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
Shihao Wang, Guo Chen, De-an Huang +6
While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative fram…
FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models
Minghan Li, Chenxi Xie, Yichen Wu +2
Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to…
MaSS13K: A Matting-level Semantic Segmentation Benchmark
Chenxi Xie, Minghan Li, Hui Zeng +2
High-resolution semantic segmentation is essential for applications such as image editing, bokeh imaging, AR/VR, etc. Unfortunately, existing datasets often have limited resolution…
DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
Chenxi Xie, Minghan Li, Shuai Li +3
Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results. Conventional…
Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion
Chaodong Xiao, Minghan Li, Zhengqiang Zhang +2
Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face…