AI Paper Atlas

Research map / Detection and segmentation / CNN features

Rethinking Neuromorphic Object Detection with Hybrid Dynamic Interaction Transformers

Dianze Li, Jianing Li, Xu Liu, Zhaokun Zhou, Xiaopeng Fan B, Yonghong Tian

IJCV 2026 · Detection and segmentation › CNN features · approach: Spiking event-camera detection · 11 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 relative semantic embedding (semantic-enhanced self-attention) (ablation)Swin Transformer baseline · DSEC-DetectionmAP: 0.269 -> 0.277Improved
add event stream through the Spiking Swin Transformer branch (ablation)HDI-Former · DSEC-DetectionmAP: 0.277 -> 0.284Improved
add dynamic interaction between ANN and SNN branches (ablation)HDI-Former · DSEC-DetectionmAP: 0.284 -> 0.291Improved
add dynamic interaction between ANN and SNN branches (ablation)HDI-Former · DSEC-DetectionmAP50: 0.511 -> 0.522Improved
add dynamic interaction between ANN and SNN branches (ablation)HDI-Former · PKU-DAVIS-SODmAP50: 0.501 -> 0.516Improved
use Spiking Swin Transformer in place of EMS-YOLO for event input (ablation)SNN branch · DSEC-DetectionmAP: 0.082 -> 0.116Improved
use spiking instead of ANN Swin-T on event data (ablation)Swin-T · Gen1mAP: 0.296 -> 0.291Hurt
use spiking instead of ANN Swin-T on event data (ablation)Swin-T · DSEC-Detection (events)mAP: 0.133 -> 0.116Hurt
set SNN timestep T=5 instead of 1 (ablation)Spiking Swin-T · Gen1mAP: 0.286 -> 0.291Improved
set SNN timestep T=5 instead of 9 (ablation)Spiking Swin-T · Gen1mAP: 0.286 -> 0.291Improved
apply dynamic interaction in 4 layers instead of 0 (ablation)HDI-Former · DSEC-DetectionmAP: 0.284 -> 0.291Improved
apply dynamic interaction in 8 layers instead of 4 (ablation)HDI-Former · DSEC-DetectionmAP: 0.291 -> 0.286Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

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