AI Paper Atlas

Research map / Detection and segmentation / CNN features

Video Object Detection via Object-level Temporal Aggregation

Chun-Han Yao, Chen Fang, Xiaohui Shen, Yangyue Wan, Ming-Hsuan Yang

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 33 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 confidence reassignment (temporal max) (ablation)YOLOv3-SPP + KCF · ImageNet VID val (YOLOv3-SPP + KCF, Dbase=1)mAP: 58.6 -> 62.1Improved
add class probability aggregation (gamma=1.0) to confidence reassignment (ablation)YOLOv3-SPP + KCF · ImageNet VID val (YOLOv3-SPP + KCF, Dbase=1)mAP: 62.1 -> 64.4Improved
raise gamma from 0.6 to 1.0 in class probability aggregation (ablation)YOLOv3-SPP + KCF · ImageNet VID val (YOLOv3-SPP + KCF, Dbase=1)mAP: 63.8 -> 64.4Improved
add box coordinate refinement (ablation)YOLOv3-SPP + KCF · ImageNet VID val (YOLOv3-SPP + KCF, Dbase=1)mAP: 64.4 -> 64.8Improved
replace heuristic aggregation with LSTM-based aggregation (ablation)YOLOv3-SPP + KCF · ImageNet VID val (YOLOv3-SPP + KCF, Dbase=1)mAP: 64.8 -> 65.8Improved
fine-tune detector on VID+DET+COCO instead of COCO only (ablation)YOLOv3-SPP + KCF + LSTM · ImageNet VID val (14 COCO classes, Dbase=1)mAP: 62.6 -> 66.6Improved
train aggregation without fine-tuning detector on VID (ablation)CenterNet + KCF + LSTM · ImageNet VID val (14 COCO classes, Dbase=1)mAP gain: +3.7 -> +4.3No clear effect
use RL keyframe scheduler instead of fixed interval (ablation)YOLOv3-SPP + KCF · ImageNet VID val (LSTM aggregation, Dbase=7)mAP: 60.6 -> 63.2Improved
use heuristic keyframe scheduler instead of fixed interval (ablation)YOLOv3-SPP + KCF · ImageNet VID val (LSTM aggregation, Dbase=7)mAP: 60.6 -> 61.2Improved
use RL scheduler instead of fixed interval (cost in speed) (ablation)YOLOv3-SPP + KCF · ImageNet VID val (LSTM aggregation, Dbase=7)speed (fps): 37.1 -> 31.4Hurt
replace KCF with SiamFC tracker (ablation)YOLOv3-SPP + RL · ImageNet VID val (LSTM aggregation, Dbase=7)mAP: 63.2 -> 63.7Improved
replace KCF with SiamFC tracker (ablation)YOLOv3-SPP + RL · ImageNet VID val (LSTM aggregation, Dbase=7)speed (fps): 31.4 -> 20.2Hurt

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