AI Paper Atlas

Research map / Detection and segmentation / CNN features

Objects Do Not Disappear: Video Object Detection by Single-Frame Object Location Anticipation

Xin Liu, Fatemeh Karimi Nejadasl, Jan C. van Gemert, Olaf Booij, Silvia L. Pintea

ICCV 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 14 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 motion anticipation supervision with simulated smooth motion (ablation)static detector on MovingDigits · MovingDigits keyframekeyframe mAP (%): 73.51 -> 76.57Improved
supervise with randomized (non-smooth) box positions between keyframes (ablation)static detector on MovingDigits · MovingDigits keyframekeyframe mAP (%): 73.51 -> 62.68Hurt
use annotated ground-truth motion instead of simulated motion (ablation)trajectory anticipation · MovingDigits keyframekeyframe mAP (%): 76.57 -> 79.31Improved
use trajectory loss L_traj instead of bag loss L_bag (ablation)trajectory network · ImageNet VID subset, T=8mAP (%): 83.97 -> 86.15Improved
predict offsets between neighboring boxes instead of box coordinates (ablation)trajectory network · ImageNet VID subsetmAP (%): +0.81% (T=4), +0.89% (T=8)Improved
use only the L_bag(delta) term without L_sum (ablation)L_traj · ImageNet VID subset, T=8mAP (%): 86.15 -> 79.73Hurt
use only L_sum without L_bag(delta) (ablation)L_traj · ImageNet VID subset, T=4mAP (%): 89.20 -> 87.95Hurt
sparse annotation loss with interpolated trajectories instead of full supervision (ablation)L_traj · ImageNet VID subset keyframes, T=4keyframe mAP (%): 91.03 -> 90.76No clear effect
use only the offset term in the sparse annotation loss (ablation)L_traj^(sa) · ImageNet VID subset keyframes, T=4keyframe mAP (%): 90.76 -> 74.61Hurt
predict longer trajectories (sample fewer keyframes) (ablation)full method · ImageNet VID subsetmAP vs FPS: mAP 89.2% at 39.6 FPS; noticeable drop beyond 10 framesMixed
predict trajectories from keyframes instead of per-frame detection on ImageNet VIDFaster RCNN R101 · ImageNet VID valmAP (%): 73.6 -> 87.2Improved
add sparse-annotation trajectory loss with interpolated pseudo trajectoriesFaster RCNN · Waymo Open AP/L1AP/L1 (%): 55.66 -> 64.53Improved

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