AI Paper Atlas

Research map / Detection and segmentation / CNN features

ViP-CNN: Visual Phrase Guided Convolutional Neural Network

Yikang Li, Wanli Ouyang, Xiaogang Wang, Xiao'ou Tang

CVPR 2017 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 254 citations (OpenAlex)

Check 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 phrase-guided message passing (PMPS) across phrase components (ablation)ViP-CNN · Visual Relationship; visual phrase detectionRec@100: 16.41 -> 26.07Improved
Add phrase-guided message passing (PMPS) across phrase components (ablation)ViP-CNN · Visual Relationship; visual relationship detectionRec@100: 12.75 -> 19.08Improved
Replace designed PMPS information flow with direct branch concatenation (ablation)ViP-CNN · Visual Relationship; visual phrase detectionRec@100: 26.07 -> 18.90Hurt
Replace PMPS with RNN message passing (ablation)ViP-CNN · Visual Relationship; visual relationship detectionRec@100: 19.08 -> 13.25Hurt
Use triplet NMS before detection rather than random triplet selection (ablation)ViP-CNN · Visual Relationship; visual phrase detectionRec@100: 23.66 -> 26.07Improved
Add triplet NMS before detection rather than omit NMS (ablation)ViP-CNN · Visual Relationship; visual phrase detectionRec@100: 16.28 -> 26.07Improved
Move NMS to after detection instead of before detection (ablation)ViP-CNN · Visual Relationship; visual phrase detectionRec@100: 26.07 -> 27.24Improved
Move NMS to after detection instead of before detection (ablation)ViP-CNN · Visual Relationship; visual relationship detectionRec@100: 19.08 -> 19.81Improved
Share subject and object branch parameters except message-passing parameters (ablation)ViP-CNN · Visual Relationship; visual phrase detectionRec@100: 26.07 -> 27.91Improved
Share subject and object branch parameters except message-passing parameters (ablation)ViP-CNN · Visual Relationship; visual relationship detectionRec@100: 19.08 -> 20.01Improved
Add PMPS (ablation)ViP-CNN · VGR-Dense; visual phrase detectionRec@100: 9.98 -> 16.75Improved
Add PMPS (ablation)ViP-CNN · VGR-Dense; visual relationship detectionRec@100: 7.89 -> 11.81Improved

Later papers that compared with this method

1 later accepted paper reports VIP-CNN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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