AI Paper Atlas

Research map / Detection and segmentation / CNN features

Progressive Sparse Local Attention for Video Object Detection

Chaoxu Guo, Bin Fan, Jie Gu, Qian Zhang, Shiming Xiang, Veronique Prinet, Chunhong Pan

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 107 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 Recursive Feature Updating (RFU) (ablation)PSLA (a) · ImageNet VID valmAP: 74.4 -> 75.8Improved
add Dense Feature Transforming Quality Net (ablation)PSLA (b) · ImageNet VID valmAP: 75.8 -> 77.1Improved
add RFU and Quality Net to Nonlocal propagation (ablation)Nonlocal_S · ImageNet VID valmAP: 72.1 -> 74.1Improved
add RFU and Quality Net to MatchTrans propagation (ablation)MatchTrans_S · ImageNet VID valmAP: 72.5 -> 75.2Improved
add RFU and Quality Net to DensePSLA propagation (ablation)DensePSLA_S · ImageNet VID valmAP: 73.6 -> 75.7Improved
use progressively sparse local region instead of dense local region (ablation)DensePSLA_S · ImageNet VID val (max displacement 4)mAP: 73.6 -> 74.4Improved
use local progressive sparse attention instead of global Nonlocal (ablation)Nonlocal_S · ImageNet VID valmAP: 72.1 -> 74.4Improved
use softmax-normalized dense local PSLA instead of MatchTrans accumulation (ablation)MatchTrans_S · ImageNet VID val (max displacement 3)mAP: 71.5 -> 73.7Improved
replace optical flow propagation (DFF) with PSLA, key frame interval 35DFF re-implementation · ImageNet VID valmAP: 67.5 -> 68.5Improved
replace optical flow propagation (DFF) with PSLA, key frame interval 15DFF re-implementation · ImageNet VID valmAP: 72.2 -> 72.9Improved
increase max displacement from 2 to 4PSLA (a) · ImageNet VID valmAP: 73.6 -> 74.4Improved
add DCN to the ResNet101 backbonePSLA · ImageNet VID valmAP: 77.1 -> 80.0Improved

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