5 papers
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Yue Feng, Jingjing Li, Qijia Lu +9
The rapid advancement of AI-driven video generation has transformed content creation, while simultaneously increasing the risk of misinformation through localized manipulations in…
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
Jiaming Zhang, Shengming Cao, Rui Li +8
Preserving first-frame identity while ensuring precise motion control is a fundamental challenge in human image animation. The Image-to-Motion Binding process of the dominant Refer…
SAM 2++: Tracking Anything at Any Granularity
Jiaming Zhang, Cheng Liang, Yichun Yang +7
Due to the varying granularity of target states across different tasks, most existing trackers are tailored to a single task, which specificity limits their generalization, prevent…
GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates
Xingyu Luo, Yidong Cai, Jie Liu +3
Vision-language tracking has gained increasing attention in many scenarios. This task simultaneously deals with visual and linguistic information to localize objects in videos. Des…
MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
Chenhui Zhu, Yilu Wu, Shuai Wang +2
Image-to-video generation has made remarkable progress with the advancements in diffusion models, yet generating videos with realistic motion remains highly challenging. This diffi…