# PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN

arXiv: https://arxiv.org/abs/1708.01956 · HTML: https://mlsanity.com/paper/1708.01956/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2017.

## Built on by (most cited first, 25 of 25)

- [WRENCH: A Comprehensive Benchmark for Weak Supervision](https://mlsanity.com/paper/2109.11377/) (2021)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Learning to Generate Scene Graph from Natural Language Supervision](https://mlsanity.com/paper/2109.02227/) (2021)
- [Linguistic Structures as Weak Supervision for Visual Scene Graph Generation](https://mlsanity.com/paper/2105.13994/) (2021)
- [Visual Distant Supervision for Scene Graph Generation](https://mlsanity.com/paper/2103.15365/) (2021)
- [Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions](https://mlsanity.com/paper/2311.17048/) (2023)
- [Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation](https://mlsanity.com/paper/2208.01834/) (2022)
- [TextPSG: Panoptic Scene Graph Generation from Textual Descriptions](https://mlsanity.com/paper/2310.07056/) (2023)
- [Weakly Supervised Relative Spatial Reasoning for Visual Question Answering](https://mlsanity.com/paper/2109.01934/) (2021)
- [Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning](https://mlsanity.com/paper/2303.01313/) (2023)
- [Can Transformers Capture Spatial Relations between Objects?](https://mlsanity.com/paper/2403.00729/) (2024)
- [Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM](https://mlsanity.com/paper/2502.18863/) (2025)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions](https://mlsanity.com/paper/2110.03562/) (2021)
- [2.5D Visual Relationship Detection](https://mlsanity.com/paper/2104.12727/) (2021)
- [Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions](https://mlsanity.com/paper/2106.08543/) (2021)
- [Human-Object Interaction Detection via Weak Supervision](https://mlsanity.com/paper/2112.00492/) (2021)
- [Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels](https://mlsanity.com/paper/2309.05069/) (2023)
- [Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling](https://mlsanity.com/paper/2404.02527/) (2024)
- [A Review of Human-Object Interaction Detection](https://mlsanity.com/paper/2408.10641/) (2024)
- [Topic Scene Graph Generation by Attention Distillation from Caption](https://mlsanity.com/paper/2110.05731/) (2021)
- [STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning](https://mlsanity.com/paper/2309.06680/) (2023)
- [FreeA: Human-object Interaction Detection using Free Annotation Labels](https://mlsanity.com/paper/2403.01840/) (2024)
- [UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding](https://mlsanity.com/paper/2406.16372/) (2024)
- [RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection](https://mlsanity.com/paper/2604.00507/) (2026)

## Abstract (arXiv)

We aim to tackle a novel vision task called Weakly Supervised Visual Relation Detection (WSVRD) to detect "subject-predicate-object" relations in an image with object relation groundtruths available only at the image level. This is motivated by the fact that it is extremely expensive to label the combinatorial relations between objects at the instance level. Compared to the extensively studied problem, Weakly Supervised Object Detection (WSOD), WSVRD is more challenging as it needs to examine a large set of regions pairs, which is computationally prohibitive and more likely stuck in a local optimal solution such as those involving wrong spatial context. To this end, we present a Parallel, Pairwise Region-based, Fully Convolutional Network (PPR-FCN) for WSVRD. It uses a parallel FCN architecture that simultaneously performs pair selection and classification of single regions and region pairs for object and relation detection, while sharing almost all computation shared over the entire image. In particular, we propose a novel position-role-sensitive score map with pairwise RoI pooling to efficiently capture the crucial context associated with a pair of objects. We demonstrate the superiority of PPR-FCN over all baselines in solving the WSVRD challenge by using results of extensive experiments over two visual relation benchmarks.