AI Paper Atlas

Research map / Detection and segmentation / CNN features

SODFormer: Streaming Object Detection With Transformer Using Events and Frames

Dianze Li, Yonghong Tian, Jianing Li

TPAMI 2023 · Detection and segmentation › CNN features · approach: Spiking event-camera detection · 71 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 temporal transformer (ablation)Deformable DETR RGB baseline · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.461 -> 0.489Improved
add DVS events with averaging fusion (ablation)temporal transformer on frames · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.489 -> 0.494Improved
replace averaging with asynchronous attention-based fusion (ablation)SODFormer · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.494 -> 0.504Improved
replace concatenation with asynchronous attention-based fusion (ablation)SODFormer · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.478 -> 0.504Improved
replace NMS post-fusion with asynchronous attention-based fusion (ablation)SODFormer · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.438 -> 0.504Improved
increase temporal aggregation size from 1 to 9 (ablation)SODFormer frames · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.461 -> 0.489Improved
increase temporal aggregation size from 9 to 13 (ablation)SODFormer frames · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.489 -> 0.488No clear effect
add DVS events to frames (ablation)SODFormer baseline · Motion blur scenariomAP50: 0.419 -> 0.432Improved
add DVS events to framesSODFormer baseline · Low-light scenariomAP50: 0.351 -> 0.374Improved
add DVS events to framesSODFormer baseline · Normal scenariomAP50: 0.557 -> 0.569Improved
use temporal transformer over feed-forward/recurrent detectors (frames)SODFormer baseline · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.456 -> 0.489Improved
use temporal transformer over best event detector (events)SODFormer baseline · PKU-DAVIS-SOD test (all scenarios)mAP50: 0.307 -> 0.334Improved

Later papers that compared with this method

1 later accepted paper reports SODFormer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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