AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Where to Focus for Efficient Video Object Detection

Zhengkai Jiang, Yu Liu, Ceyuan Yang, Jihao Liu, Peng Gao, Qian Zhang, Shiming Xiang, Chunhong Pan

ECCV 2020 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 73 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 learning of sampled locations (Gaussian init) (ablation)LSTS · ImageNet VID valmAP (%): 75.5 -> 77.2Improved
add learning of sampled locations (Uniform init) (ablation)LSTS · ImageNet VID valmAP (%): 75.5 -> 76.8Improved
use Gaussian instead of Uniform initialization of sampled locations (ablation)LSTS · ImageNet VID valmAP (%): 76.8 -> 77.2Improved
use LSTS instead of Non-Local for feature propagation (ablation)SRFU+DFA framework · ImageNet VID valmAP (%): 74.2 -> 77.2Improved
use LSTS instead of MatchTrans for feature propagation (ablation)SRFU+DFA framework · ImageNet VID valmAP (%): 75.5 -> 77.2Improved
use LSTS instead of optical flow warping (full model) (ablation)SRFU+DFA framework · ImageNet VID valmAP (%): 76.1 -> 77.2Improved
use LSTS instead of optical flow warping (full model) (ablation)SRFU+DFA framework · ImageNet VID valparameters (M): 100.5 -> 64.5Improved
use LSTS instead of optical flow warping (full model) (ablation)SRFU+DFA framework · ImageNet VID valruntime (FPS): 18.9 -> 23.0Improved
add quality-aware memory update to keyframes (ablation)SRFU · ImageNet VID valmAP (%): 73.5 -> 75.9Improved
quality-aware instead of fixed 0.5 weights for keyframe memory update (ablation)SRFU · ImageNet VID valmAP (%): 75.8 -> 75.9Improved
add non-keyframe aggregation (DFA) (ablation)DFA · ImageNet VID valmAP (%): 75.9 -> 76.4Improved
add non-keyframe transform unit (ablation)DFA · ImageNet VID valmAP (%): 76.4 -> 76.5Improved

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