AI Paper Atlas

Research map / Detection and segmentation / CNN features

Object Guided External Memory Network for Video Object Detection

Hanming Deng, Yang Hua, Tao Song, Zongpu Zhang, Zhengui Xue, Ruhui Ma, Neil Robertson, Haibing Guan

ICCV 2019 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 110 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 pixel-level object-guided memory Mpix (ablation)R-FCN · ImageNet VID valmAP (%): 73.8 -> 78.8Improved
add instance-level memory Minst (ablation)R-FCN · ImageNet VID valmAP (%): 73.8 -> 74.8Improved
add instance memory Minst to pixel memory (ablation)Mpix · ImageNet VID valmAP (%): 78.8 -> 79.3Improved
add pixel memory Mpix (ablation)R-FCN · ImageNet VID val (fast motion)mAP (%): 52.4 -> 60.0Improved
add instance memory to pixel memory (ablation)Mpix · ImageNet VID val (slow motion)mAP (%): 85.8 -> 86.2Improved
add both memories (ablation)R-FCN · ImageNet VID valruntime (ms): 72 -> 112Hurt
down-sample non-key frames to 1/2 with memory (ablation)Ours · ImageNet VID valmAP (%): 73.8 -> 76.8Improved
down-sample non-key frames to 1/3 with memory (ablation)Ours · ImageNet VID valmAP (%): 73.8 -> 74.4Improved
down-sample non-key frames to 1/4 with memory (ablation)Ours · ImageNet VID valmAP (%): 73.8 -> 71.5Hurt
add deformable convolution (DCN) to feature networkOurs · ImageNet VID valmAP (%): 79.3 -> 80.0Improved
apply Seq-NMS post-processingOurs · ImageNet VID valmAP (%): 79.3 -> 80.8Improved
replace flow-based alignment with attentional read (vs FGFA)Ours · ImageNet VID val (fast motion)mAP (%): 57.6 -> 61.1Improved

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