# Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition

arXiv: https://arxiv.org/abs/1807.04979 · HTML: https://mlsanity.com/paper/1807.04979/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2018.

## Built on by (most cited first, 30 of 41)

- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Target Adaptive Context Aggregation for Video Scene Graph Generation](https://mlsanity.com/paper/2108.08121/) (2021)
- [From General to Specific: Informative Scene Graph Generation via Balance Adjustment](https://mlsanity.com/paper/2108.13129/) (2021)
- [Structured Sparse R-CNN for Direct Scene Graph Generation](https://mlsanity.com/paper/2106.10815/) (2021)
- [Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries](https://mlsanity.com/paper/2105.02170/) (2021)
- [RU-Net: Regularized Unrolling Network for Scene Graph Generation](https://mlsanity.com/paper/2205.01297/) (2022)
- [Devil's on the Edges: Selective Quad Attention for Scene Graph Generation](https://mlsanity.com/paper/2304.03495/) (2023)
- [SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction](https://mlsanity.com/paper/2309.15702/) (2023)
- [BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation](https://mlsanity.com/paper/2109.05346/) (2021)
- [Vision Relation Transformer for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.09472/) (2023)
- [Adaptive Fine-Grained Predicates Learning for Scene Graph Generation](https://mlsanity.com/paper/2207.04602/) (2022)
- [Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs](https://mlsanity.com/paper/2305.08522/) (2023)
- [Joint learning of object graph and relation graph for visual question answering](https://mlsanity.com/paper/2205.04188/) (2022)
- [ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection](https://mlsanity.com/paper/2109.04047/) (2021)
- [DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation](https://mlsanity.com/paper/2503.13957/) (2025)
- [Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation](https://mlsanity.com/paper/2409.10262/) (2024)
- [One-shot Scene Graph Generation](https://mlsanity.com/paper/2202.10824/) (2022)
- [2.5D Visual Relationship Detection](https://mlsanity.com/paper/2104.12727/) (2021)
- [Single-Stage Visual Relationship Learning using Conditional Queries](https://mlsanity.com/paper/2306.05689/) (2023)
- [Neural Message Passing for Visual Relationship Detection](https://mlsanity.com/paper/2208.04165/) (2022)
- [Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning](https://mlsanity.com/paper/2401.14626/) (2024)
- [Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2301.00351/) (2023)
- [AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generation](https://mlsanity.com/paper/2404.07788/) (2024)
- [RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.10168/) (2026)
- [Explore Contextual Information for 3D Scene Graph Generation](https://mlsanity.com/paper/2210.06240/) (2022)
- [Topic Scene Graph Generation by Attention Distillation from Caption](https://mlsanity.com/paper/2110.05731/) (2021)

## Abstract (arXiv)

Recognizing visual relationships <subject-predicate-object> among any pair of localized objects is pivotal for image understanding. Previous studies have shown remarkable progress in exploiting linguistic priors or external textual information to improve the performance. In this work, we investigate an orthogonal perspective based on feature interactions. We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors. To this end, we present two new pooling cells to encourage feature interactions: (i) Contrastive ROI Pooling Cell, which has a unique deROI pooling that inversely pools local object features to the corresponding area of global predicate features. (ii) Pyramid ROI Pooling Cell, which broadcasts global predicate features to reinforce local object features.The two cells constitute a Spatiality-Context-Appearance Module (SCA-M), which can be further stacked consecutively to form our final Zoom-Net.We further shed light on how one could resolve ambiguous and noisy object and predicate annotations by Intra-Hierarchical trees (IH-tree). Extensive experiments conducted on Visual Genome dataset demonstrate the effectiveness of our feature-oriented approach compared to state-of-the-art methods (Acc@1 11.42% from 8.16%) that depend on explicit modeling of linguistic interactions. We further show that SCA-M can be incorporated seamlessly into existing approaches to improve the performance by a large margin. The source code will be released on https://github.com/gjyin91/ZoomNet.