mlsanityData to 7 Oct 2026

VPN: Video Provenance Network for Robust Content Attribution

arXiv 2109.10038 ↗First posted 21 Sep 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We present VPN - a content attribution method for recovering provenance information from videos shared online. Platforms, and users, often transform video into different quality, codecs, sizes, shapes, etc. or slightly edit its content such as adding text or emoji, as they are redistributed online. We learn a robust search embedding for matching such video, invariant to these transformations, using full-length or truncated video queries. Once matched against a trusted database of video clips, associated information on the provenance of the clip is presented to the user. We use an inverted index to match temporal chunks of video using late-fusion to combine both visual and audio features. In both cases, features are extracted via a deep neural network trained using contrastive learning on a dataset of original and augmented video clips. We demonstrate high accuracy recall over a corpus of 100,000 videos.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 27 of its 67 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

27 of 67 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  5. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  6. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 641
  7. 2019The Deepfake Detection Challenge (DFDC) Preview Datasetcited by 208
  8. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  9. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  10. 2017HashNet: Deep Learning to Hash by Continuationcited by 121
  11. 2019Central Similarity Quantization for Efficient Image and Video Retrievalcited by 77
  12. 2015Feature Learning based Deep Supervised Hashing with Pairwise Labelscited by 59
15 more
  1. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  2. 2016Convolutional Recurrent Neural Networks for Music Classificationcited by 49
  3. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  4. 2017Deep Supervised Discrete Hashingcited by 36
  5. 2017Asymmetric Deep Supervised Hashingcited by 35
  6. 2014Hashing for Similarity Search: A Surveycited by 34
  7. 2017Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveformscited by 27
  8. 2018Image Provenance Analysis at Scalecited by 16
  9. 2021OSCAR-Net: Object-centric Scene Graph Attention for Image Attributioncited by 15
  10. 2016Deep convolutional neural networks for predominant instrument recognition in polyphonic musiccited by 11
  11. 2017A Tutorial on Deep Learning for Music Information Retrievalcited by 9
  12. 2018ARCHANGEL: Trusted Archives of Digital Public Documentscited by 7
  13. 2019Push for Quantization: Deep Fisher Hashingcited by 6
  14. 2017Revisiting the problem of audio-based hit song prediction using convolutional neural networkscited by 4
  15. 2015An End-to-End Neural Network for Polyphonic Piano Music Transcriptioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 1; 2025: 0; 2026: 1.

7 papers.

  1. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 54
  2. 2022RepMix: Representation Mixing for Robust Attribution of Synthesized Imagescited by 39
  3. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenancecited by 21
  4. 2023Audio-Visual Contrastive Learning with Temporal Self-Supervisioncited by 18
  5. 2023VADER: Video Alignment Differencing and Retrievalcited by 6
  6. 2022ARIA: Adversarially Robust Image Attribution for Content Provenancecited by 1
  7. 2026SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defensecited by 0