AI Paper Atlas

Research map / Video / Video segmentation and tracking

Seeing Tree Structure from Vibration

Tianfan Xue, Jiajun Wu, Zhoutong Zhang, Chengkai Zhang, Joshua B. Tenenbaum, William T. Freeman

ECCV 2018 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 13 citations (OpenAlex)

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 changedWhereMeasuredEffect
add vibration spectrum cues to appearance cues (ablation)tree structure inference · Tree structure videos (avg over 17 videos)parent accuracy (%): 65.7 -> 79.3Improved
add vibration spectrum cues to appearance cues (ablation)tree structure inference · Tree structure videos (avg over 17 videos)edit distance: 13.7 -> 7.0Improved
use spectral motion features instead of raw optical flow (ablation)appearance + motion · Tree structure videos (avg over 17 videos)parent accuracy (%): 73.5 -> 79.3Improved
use spectral motion features instead of KLT tracking (ablation)appearance + motion · Tree structure videos (avg over 17 videos)parent accuracy (%): 73.8 -> 79.3Improved
use spectral motion features instead of raw optical flow (ablation)appearance + motion · Tree structure videos (avg over 17 videos)edit distance: 9.5 -> 7.0Improved
use appearance plus vibration instead of hierarchical motion segmentationtree structure inference · Tree structure videos (avg over 17 videos)parent accuracy (%): 56.3 -> 79.3Improved
add vibration cues on tree video A2 (ablation)appearance only · Tree video A2parent accuracy (%): 31 -> 45Improved
add vibration cues on tree video A3 (ablation)appearance only · Tree video A3parent accuracy (%): 90 -> 100Improved
use ours on retinal vessels instead of A+Flow or A+Trackstructure inference · Retinal videoedit distance: 7 -> 4Improved
increase video frame rate from 30 to 200 FPSOurs · High-speed videos H1-H6parent accuracy (%): 69 -> 77Mixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy