AI Paper Atlas

Research map / Detection and segmentation / CNN features

Practical Video Object Detection via Feature Selection and Aggregation

Yuheng Shi, Tong Zhang, XiaoJie Guo

IJCV 2026 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 17 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 feature selection and aggregation (TopK+NMS) to the base detector (ablation)YOLOX-S · ImageNet VID valAP50: 69.5 -> 75.4Improved
add affinity matrix to the aggregation (ablation)YOLOV (TopK+NMS) · ImageNet VID valAP50: 75.4 -> 76.9Improved
add average pooling over reference features (ablation)YOLOV (TopK+NMS) · ImageNet VID valAP50: 76.9 -> 77.3Improved
add regression-branch aggregation FAM_r on top of TopK+NMS (ablation)YOLOV++ · ImageNet VID valAP50: 77.3 -> 75.3Hurt
use Thresh instead of TopK+NMS together with FAM_r (ablation)YOLOV++ · ImageNet VID valAP50: 75.3 -> 78.7Improved
add FAM_r under Thresh selection (ablation)YOLOV++ · ImageNet VID valAP50: 76.4 -> 78.7Improved
use global instead of local reference frame sampling (4 global vs 39 local) (ablation)YOLOV++-S · ImageNet VID valAP50: 74.1 -> 75.7Improved
increase global reference frames from 4 to 31 (ablation)YOLOV++-S · ImageNet VID valAP50: 75.7 -> 78.7Improved
raise average-pooling threshold tau from 0 to 0.75 (ablation)YOLOV++-S · ImageNet VID valAP50: 77.1 -> 78.7Improved
set tau to 1 (no pooling selection) vs 0.75 (ablation)YOLOV++-S · ImageNet VID valAP50: 78.7 -> 78.3Hurt
upgrade YOLOV to YOLOV++YOLOX-S · ImageNet VID valAP50: 77.3 -> 78.7Improved
apply the strategy to PPYOLOE-SPPYOLOE-S · ImageNet VID valAP50: 69.5 -> 75.6Improved

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