AI Paper Atlas

Research map / Detection and segmentation / CNN features

Fast Object Detection in Compressed Video

Shiyao Wang, Hongchao Lu, Zhidong Deng

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 71 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-vector warping to LSTM memory (ablation)LSTM + residual · ImageNet VID valmAP (%): 66.1 -> 72.1Improved
add motion-vector warping to LSTM only memory (ablation)LSTM only · ImageNet VID valmAP (%): 66.3 -> 71.3Improved
add residual errors without motion vectors (ablation)LSTM memory · ImageNet VID valmAP (%): 66.3 -> 66.1Hurt
add motion vectors to fast-moving objects (ablation)LSTM memory · ImageNet VID val (fast motion)mAP (%): 27.7 -> 38.5Improved
add residual errors on top of motion vectors and LSTM (ablation)MV + LSTM · ImageNet VID valmAP (%): 71.3 -> 72.1Improved
add LSTM to motion vectors and residual errors (ablation)MV + residual · ImageNet VID valmAP (%): 70.3 -> 72.1Improved
add LSTM to motion vectors and residual errors (ablation)MV + residual · ImageNet VID valspeed (fps): 51.3 -> 41.7Hurt
add pyramidal feature attention (ablation)MV + residual + LSTM · ImageNet VID valmAP (%): 72.1 -> 73.0Improved
add pyramidal feature attention (ablation)MV + residual + LSTM · ImageNet VID val (medium motion)mAP (%): 72.0 -> 73.4Improved
add pyramidal feature attention (ablation)MV + residual + LSTM · ImageNet VID val (slow motion)mAP (%): 83.6 -> 84.7Improved
add pyramidal feature attention (ablation)MV + residual + LSTM · ImageNet VID val (fast motion)mAP (%): 44.2 -> 43.7Hurt
add pyramidal feature attention (ablation)MV + residual + LSTM · ImageNet VID valspeed (fps): 41.7 -> 40.5Hurt

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