AI Paper Atlas

Research map / Detection and segmentation / CNN features

Per‑Object IoU Forecasting for Deadline‑Aware Real‑Time Embedded Detection Control

Erfan Foorginejad, Akshar Chavan, Marco Brocanelli

ECCV 2026 · Detection and segmentation › CNN features · approach: Box regression and loss design · 0 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
model deadlines per object instead of frame-level average (OLAP-tiny vs FLAP) (ablation)deadline predictor · Deadline predictionRMSE: 32.3% average RMSE reductionImproved
add object dynamics features (speed, location, size) to OLAP-tiny (ablation)OLAP · Deadline predictionRMSE: 34.5% additional RMSE reductionImproved
use OLAP deadlines in controller instead of ROMAOLAP-C · Streaming detection, Argoverse-HD + MOT17 (71 scenarios), Intel NodesAP: +39% over ROMA (0.287)Improved
use OLAP-C instead of ROMA on Apple M3OLAP-C · Streaming detection, Argoverse-HD + MOT17 (71 scenarios), Apple M3sAP: +24.6% over ROMAImproved
use OLAP-C instead of ROMA on JetsonOLAP-C · Streaming detection, Argoverse-HD + MOT17 (71 scenarios), JetsonsAP: +1.3% over ROMA (0.408)No clear effect
adaptive detector selection instead of best static detectorROMA · Streaming detection, Argoverse-HD + MOT17 (71 scenarios), Intel NodesAP: +25% over Best StaticImproved
OLAP-C vs frame-level FLAP for longer deadlines (>15 frames)OLAP · Deadline predictionerror: up to 67% and 56% average improvement but conservativeMixed
FLAP on short deadlines (up to 6 frames)FLAP · Deadline predictiondeadline accuracyNo clear effect
raise priority weight of critical object to 10 (ablation)OLAP-C · MOT17-13 pedestrian exampleper-object IoU: critical object IoU up, non-critical average IoU downMixed

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