AI Paper Atlas

Research map / Video / Video segmentation and tracking

Data-Driven Feature Tracking for Event Cameras With and Without Frames

Nico Messikommer, Carter Fang, Mathias Gehrig, Giovanni Cioffi, Davide Scaramuzza

TPAMI 2025 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 16 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 correlation map (ablation)reference model · EDSExpected feature age: 0.341 -> 0.383Improved
add correlation map (ablation)reference model · ECExpected feature age: 0.684 -> 0.787Improved
add recurrence in feature encoder (ablation)reference model · EDSExpected feature age: 0.301 -> 0.383Improved
add recurrence in feature encoder (ablation)reference model · ECExpected feature age: 0.606 -> 0.787Improved
add augmentation during synthetic training (ablation)reference model · EDSExpected feature age: 0.178 -> 0.383Improved
add augmentation during synthetic training (ablation)reference model · ECExpected feature age: 0.599 -> 0.787Improved
add frame attention module (ablation)reference model · EDSExpected feature age: 0.383 -> 0.451Improved
add frame attention module (ablation)reference model · ECExpected feature age: 0.787 -> 0.787No clear effect
add pose supervision fine-tuning (ablation)Ref + Frame Attention · EDSExpected feature age: 0.451 -> 0.471Improved
add pose supervision fine-tuning (ablation)Ref + Frame Attention · ECExpected feature age: 0.787 -> 0.818Improved
add state variables in frame attention (ablation)Ref + Frame Attention · EDSExpected feature age: 0.385 -> 0.451Improved
replace gating network with LSTM (ablation)Ref + Frame Attention · EDSExpected feature age: 0.451 -> 0.423Hurt

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