20 papers
High-Quality Entity Segmentation and Grounding
Lu Qi, Yi-Wen Chen, Tao Zhang +4
In this work, we propose ESG, a pipeline for high-quality entity segmentation and grounding supported by a new dataset EntitySeg. At first, the proposed dataset naming EntitySeg co…
Video Prediction Transformers without Recurrence or Convolution
Yujin Tang, Lu Qi, Xiangtai Li +2
Video prediction has witnessed the emergence of RNN-based models led by ConvLSTM, and CNN-based models led by SimVP. Following the significant success of ViT, recent works have int…
Conditional Panoramic Image Generation via Masked Autoregressive Modeling
Chaoyang Wang, Xiangtai Li, Lu Qi +4
Recent progress in panoramic image generation has underscored two critical limitations in existing approaches. First, most methods are built upon diffusion models, which are inhere…
Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos
Haobo Yuan, Xiangtai Li, Tao Zhang +8
This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, whic…
Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
Ziyu Guo, Xinyan Chen, Renrui Zhang +7
Recent video generation models can produce high-fidelity, temporally coherent videos, indicating that they may encode substantial world knowledge. Beyond realistic synthesis, they…
The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA
Quanzhu Niu, Dengxian Gong, Shihao Chen +6
Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions, demanding fine-grained understanding of b…