MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing
cs.CV, cs.AI, cs.MM
Submitted: 2026-10-09
Updated: 2026-10-09
Project page: https://badaleexxx.github.io/MotionCoach-ProjectPage
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
- GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- GEMS: Agent-Native Multimodal Generation with Memory and Skills
- Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Seedance 2.0: Advancing Video Generation for World Complexity
- TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs
- CoVEBench: Can Video Editing Models Handle Complex Instructions?
- Automated Movie Generation via Multi-Agent CoT Planning
- M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning
- Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling
- VideoAgent: All-in-One Framework for Video Understanding and Editing
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models