Research map / Detection and segmentation / CNN features
ViP-CNN: Visual Phrase Guided Convolutional Neural Network
Yikang Li, Wanli Ouyang, Xiaogang Wang, Xiao'ou Tang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add phrase-guided message passing (PMPS) across phrase components (ablation) | ViP-CNN · Visual Relationship; visual phrase detection | Rec@100: 16.41 -> 26.07 | Improved |
| Add phrase-guided message passing (PMPS) across phrase components (ablation) | ViP-CNN · Visual Relationship; visual relationship detection | Rec@100: 12.75 -> 19.08 | Improved |
| Replace designed PMPS information flow with direct branch concatenation (ablation) | ViP-CNN · Visual Relationship; visual phrase detection | Rec@100: 26.07 -> 18.90 | Hurt |
| Replace PMPS with RNN message passing (ablation) | ViP-CNN · Visual Relationship; visual relationship detection | Rec@100: 19.08 -> 13.25 | Hurt |
| Use triplet NMS before detection rather than random triplet selection (ablation) | ViP-CNN · Visual Relationship; visual phrase detection | Rec@100: 23.66 -> 26.07 | Improved |
| Add triplet NMS before detection rather than omit NMS (ablation) | ViP-CNN · Visual Relationship; visual phrase detection | Rec@100: 16.28 -> 26.07 | Improved |
| Move NMS to after detection instead of before detection (ablation) | ViP-CNN · Visual Relationship; visual phrase detection | Rec@100: 26.07 -> 27.24 | Improved |
| Move NMS to after detection instead of before detection (ablation) | ViP-CNN · Visual Relationship; visual relationship detection | Rec@100: 19.08 -> 19.81 | Improved |
| Share subject and object branch parameters except message-passing parameters (ablation) | ViP-CNN · Visual Relationship; visual phrase detection | Rec@100: 26.07 -> 27.91 | Improved |
| Share subject and object branch parameters except message-passing parameters (ablation) | ViP-CNN · Visual Relationship; visual relationship detection | Rec@100: 19.08 -> 20.01 | Improved |
| Add PMPS (ablation) | ViP-CNN · VGR-Dense; visual phrase detection | Rec@100: 9.98 -> 16.75 | Improved |
| Add PMPS (ablation) | ViP-CNN · VGR-Dense; visual relationship detection | Rec@100: 7.89 -> 11.81 | Improved |
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.
- Visual Relationship Detection With Internal and External Linguistic Knowledge Distillation (ICCV 2017 · better on 2 of 2 shared results)
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.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 1 of 1 shared result
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
- Detecting Visual Relationships With Deep Relational Networks (CVPR 2017 · similarity 0.88)
- Localize, Assemble, and Predicate: Contextual Object Proposal Embedding for Visual Relation Detection (AAAI 2020 · similarity 0.87)
- VrR-VG: Refocusing Visually-Relevant Relationships (ICCV 2019 · similarity 0.86)
- Visual Translation Embedding Network for Visual Relation Detection (CVPR 2017 · similarity 0.86)
- MR-NET: Exploiting Mutual Relation for Visual Relationship Detection (AAAI 2019 · similarity 0.86)
- Multi-Modal Prompting for Open-Vocabulary Video Visual Relationship Detection (AAAI 2024 · similarity 0.85)
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.
