AI Paper Atlas

Research map / Video / Video segmentation and tracking

Sparsely Timing the Change: A Spiking Temporal Framework for Remote Sensing Interpretation

Shilong Li, Xiurui Xie, Qiugang Zhan, Luochao Wang, Yong Deng, Guisong Liu

CVPR 2026 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling

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 SpikeAdapter (GSI-P + SNN + STSpikeFuse) to a ViT-SAM Large backbonechange detection backbone · CLCDF1 (%): 78.03 -> 82.96 (vs Change3D)Improved
add SpikeAdapterchange detection backbone · SYSU-CDF1 (%): 82.66 -> 84.11 (vs CD-Lamba)Improved
add GSI-P with STSpikeFuse to TTP baseline (ablation)TTP · LEVIR-CDF1 (%): 92.10 -> 93.08Improved
use linear delay mapping instead of inverse or learned MLP (ablation)GSI-P · LEVIR-CDF1 (%): 92.84 / 92.88 -> 93.08Improved
add triangular temporal smoothing kernel (ablation)GSI-P · LEVIR-CDF1 (%): 92.65 -> 93.08Improved
use triangular kernel instead of Gaussian kernel (ablation)GSI-P · LEVIR-CDF1 (%): 92.85 -> 93.08Improved
use STSpikeFuse instead of simple addition of SNN features (ablation)SpikeAdapter · LEVIR-CDF1 (%): 92.40 -> 93.08Improved
use STSpikeFuse instead of concatenation (ablation)SpikeAdapter · LEVIR-CDF1 (%): 92.87 -> 93.08Improved
fuse attention output with backbone feature rather than using it directly (ablation)STSpikeFuse · LEVIR-CDF1 (%): 75.67 -> 92.8Improved
use learnable gate instead of addition or concatenation for final fusion (ablation)STSpikeFuse · LEVIR-CDF1 (%): 92.82 (Add) / 92.95 (Concat) vs 92.8 (Gate)No clear effect
raise input resolution from 256 to 512 (ablation)SpikeAdapter · LEVIR-CDF1 (%): 92.96 -> 93.08Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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