paper-with-me

홈 › Papers

MOVE: Motion-Guided Few-Shot Video Object Segmentation

2025-07-29 · Kaining Ying, Hengrui Hu, Henghui Ding arxiv

This work addresses motion-guided few-shot video object segmentation (FSVOS), which aims to segment dynamic objects in videos based on a few annotated examples with the same motion patterns. Existing FSVOS datasets and methods typically focus on object categories, which are static attributes that ignore the rich temporal dynamics in videos, limiting their application in scenarios requiring motion understanding. To fill this gap, we introduce MOVE, a large-scale dataset specifically designed for motion-guided FSVOS. Based on MOVE, we comprehensively evaluate 6 state-of-the-art methods from 3 different related tasks across 2 experimental settings. Our results reveal that current methods struggle to address motion-guided FSVOS, prompting us to analyze the associated challenges and propose a baseline method, Decoupled Motion Appearance Network (DMA). Experiments demonstrate that our approach achieves superior performance in few shot motion understanding, establishing a solid foundation for future research in this direction.

📄 PDF Abstract BibTeX arXiv:2507.22061

Code (0)

등록된 구현이 없습니다.

Tasks

Video Object Segmentation

Similar Papers 제목 키워드 기반

SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation

2024-11-07 · Koichi Namekata, Sherwin Bahmani, Ziyi Wu, Yash Kant 외

Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of t…

Image to Video GenerationVideo Generation

MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation

2025-02-06 · Jinbo Xing, Long Mai, Cusuh Ham, Jiahui Huang 외

This paper presents a method that allows users to design cinematic video shots in the context of image-to-video generation. Shot design, a critical aspect of filmmaking, involves meticulously planning both camera movemen…

Image to Video GenerationVideo EditingVideo Generation

Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models

2024-04-08 · Saman Motamed, Wouter Van Gansbeke, Luc van Gool

With recent advances in image and video diffusion models for content creation, a plethora of techniques have been proposed for customizing their generated content. In particular, manipulating the cross-attention layers o…

Video Editing

MotionCrafter: One-Shot Motion Customization of Diffusion Models

2023-12-08 · Yuxin Zhang, Fan Tang, Nisha Huang, Haibin Huang 외

The essence of a video lies in its dynamic motions, including character actions, object movements, and camera movements. While text-to-video generative diffusion models have recently advanced in creating diverse contents…

DisentanglementMotion DisentanglementText-to-Video GenerationVideo Editing+1

MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation

2023-11-28 · Sitong Su, Litao Guo, Lianli Gao, HengTao Shen 외

Zero-shot Text-to-Video synthesis generates videos based on prompts without any videos. Without motion information from videos, motion priors implied in prompts are vital guidance. For example, the prompt "airplane landi…

DisentanglementText-to-Video GenerationVideo GenerationZero-shot Text-to-Video Generation