794 citations · 2.8k across the 67 of their papers we have counts for
88 papers · 1 filter
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
Yaohui Wang, Xinyuan Chen, Xin Ma +17
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challengi…
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
Rui Qian, Shuangrui Ding, Xian Liu +1
Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further a…
Learning Referring Video Object Segmentation from Weak Annotation
Wangbo Zhao, Kepan Nan, Songyang Zhang +3
Referring video object segmentation (RVOS) is a task that aims to segment the target object in all video frames based on a sentence describing the object. Although existing RVOS me…
Improving Pixel-based MIM by Reducing Wasted Modeling Capability
Yuan Liu, Songyang Zhang, Jiacheng Chen +3
There has been significant progress in Masked Image Modeling (MIM). Existing MIM methods can be broadly categorized into two groups based on the reconstruction target: pixel-based…
DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
Wei Cheng, Ruixiang Chen, Wanqi Yin +18
Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing…
MMBench: Is Your Multi-modal Model an All-around Player?
Yuan Liu, Haodong Duan, Yuanhan Zhang +9
Large vision-language models (VLMs) have recently achieved remarkable progress, exhibiting impressive multimodal perception and reasoning abilities. However, effectively evaluating…