# OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution

arXiv: https://arxiv.org/abs/2108.03541 · HTML: https://mlsanity.com/paper/2108.03541/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 67 references that are in the map.
- First posted on arXiv 7 Aug 2021.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [Specifying Object Attributes and Relations in Interactive Scene Generation](https://mlsanity.com/paper/1909.05379/) (2019)
- [MovieGraphs: Towards Understanding Human-Centric Situations from Videos](https://mlsanity.com/paper/1712.06761/) (2017)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [Detecting Photoshopped Faces by Scripting Photoshop](https://mlsanity.com/paper/1906.05856/) (2019)
- [Deep Supervised Discrete Hashing](https://mlsanity.com/paper/1705.10999/) (2017)
- [Asymmetric Deep Supervised Hashing](https://mlsanity.com/paper/1707.08325/) (2017)
- [Hashing for Similarity Search: A Survey](https://mlsanity.com/paper/1408.2927/) (2014)
- [Aligning Linguistic Words and Visual Semantic Units for Image Captioning](https://mlsanity.com/paper/1908.02127/) (2019)
- [Image Provenance Analysis at Scale](https://mlsanity.com/paper/1801.06510/) (2018)
- [The PS-Battles Dataset - an Image Collection for Image Manipulation Detection](https://mlsanity.com/paper/1804.04866/) (2018)
- [ARCHANGEL: Trusted Archives of Digital Public Documents](https://mlsanity.com/paper/1804.08342/) (2018)
- [Push for Quantization: Deep Fisher Hashing](https://mlsanity.com/paper/1909.00206/) (2019)

## Built on by (most cited first, 15 of 15)

- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [RoSteALS: Robust Steganography using Autoencoder Latent Space](https://mlsanity.com/paper/2304.03400/) (2023)
- [TrustMark: Universal Watermarking for Arbitrary Resolution Images](https://mlsanity.com/paper/2311.18297/) (2023)
- [RepMix: Representation Mixing for Robust Attribution of Synthesized Images](https://mlsanity.com/paper/2207.02063/) (2022)
- [SynthID-Image: Image watermarking at internet scale](https://mlsanity.com/paper/2510.09263/) (2025)
- [ProMark: Proactive Diffusion Watermarking for Causal Attribution](https://mlsanity.com/paper/2403.09914/) (2024)
- [VIXEN: Visual Text Comparison Network for Image Difference Captioning](https://mlsanity.com/paper/2402.19119/) (2024)
- [EKILA: Synthetic Media Provenance and Attribution for Generative Art](https://mlsanity.com/paper/2304.04639/) (2023)
- [VPN: Video Provenance Network for Robust Content Attribution](https://mlsanity.com/paper/2109.10038/) (2021)
- [DECORAIT -- DECentralized Opt-in/out Registry for AI Training](https://mlsanity.com/paper/2309.14400/) (2023)
- [A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos](https://mlsanity.com/paper/2310.00670/) (2023)
- [VADER: Video Alignment Differencing and Retrieval](https://mlsanity.com/paper/2303.13193/) (2023)
- [Content ARCs: Decentralized Content Rights in the Age of Generative AI](https://mlsanity.com/paper/2503.14519/) (2025)
- [ARIA: Adversarially Robust Image Attribution for Content Provenance](https://mlsanity.com/paper/2202.12860/) (2022)
- [Learning Probabilistic Embeddings for Unsupervised Action Segmentation](https://mlsanity.com/paper/2607.05263/) (2026)

## Abstract (arXiv)

Images tell powerful stories but cannot always be trusted. Matching images back to trusted sources (attribution) enables users to make a more informed judgment of the images they encounter online. We propose a robust image hashing algorithm to perform such matching. Our hash is sensitive to manipulation of subtle, salient visual details that can substantially change the story told by an image. Yet the hash is invariant to benign transformations (changes in quality, codecs, sizes, shapes, etc.) experienced by images during online redistribution. Our key contribution is OSCAR-Net (Object-centric Scene Graph Attention for Image Attribution Network); a robust image hashing model inspired by recent successes of Transformers in the visual domain. OSCAR-Net constructs a scene graph representation that attends to fine-grained changes of every object's visual appearance and their spatial relationships. The network is trained via contrastive learning on a dataset of original and manipulated images yielding a state of the art image hash for content fingerprinting that scales to millions of images.