Research map / Video / Video generation
One-Shot Imitation Drone Filming of Human Motion Videos
Chong Xing Huang, Yuanjie Dang, Peng Chen, Xin Yan Yang, Kwang-Ting Tim Cheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace the loss of Duan et al. with the proposed action loss | action imitation module · Action prediction, fly-by | MSE linear direction: 0.86 -> 0.43 | Improved |
| replace the loss of Duan et al. with the proposed action loss | action imitation module · Action prediction, fly-by | MSE angular speed: 0.07 -> 0.04 | Improved |
| replace the loss of Duan et al. with the proposed action loss | action imitation module · Action prediction, orbiting | MSE angular speed: 0.06 -> 0.04 | Improved |
| replace the loss of Duan et al. with the proposed action loss | action imitation module · Action prediction, fly-through | MSE angular speed and direction: 0.01 -> 0.01 | No clear effect |
| add the background branch to the foreground-only input (ablation) | style classifier · Style classification, own dataset | confusion matrix accuracy | Improved |
| add the attention layer to FG+BG (ablation) | style classifier · Style classification, own dataset | confusion matrix accuracy | Improved |
| use the one-shot style-feature imitation instead of learning each style from the demo video only | drone cinematography system · Mixed-style imitation | user study score (1-5): 2.4 -> 4.2 | Improved |
Closest papers by meaning
- OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation (NeurIPS 2025 · similarity 0.82)
- Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration (ICML 2024 · similarity 0.82)
- Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion (ICLR 2025 · similarity 0.82)
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations (NeurIPS 2025 · similarity 0.82)
- Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control (NeurIPS 2024 · similarity 0.81)
- MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance (ICML 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
