[HTML][HTML] Vision transformers are active learners for image copy detection

Z Tan, W Wang, C Shan - Neurocomputing, 2024 - Elsevier
Abstract Image Copy Detection (ICD) is developed to identify and track duplicated or
manipulated images. The majority of existing methods rely on Convolutional Neural …

Replication in visual diffusion models: A survey and outlook

W Wang, Y Sun, Z Yang, Z Hu, Z Tan… - arXiv preprint arXiv …, 2024 - arxiv.org
Visual diffusion models have revolutionized the field of creative AI, producing high-quality
and diverse content. However, they inevitably memorize training images or videos …

A benchmark and asymmetrical-similarity learning for practical image copy detection

W Wang, Y Sun, Y Yang - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Image copy detection (ICD) aims to determine whether a query image is an edited copy of
any image from a reference set. Currently, there are very limited public benchmarks for ICD …

Pattern-Expandable Image Copy Detection

W Wang, Y Sun, Y Yang - International Journal of Computer Vision, 2024 - Springer
Open-world visual recognition aims to empower models to identify objects in real-world
settings, particularly when they encounter domains or categories that are not included in the …

VL: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval

W Wang, Y Sun, Z Yang, Y Yang - arXiv preprint arXiv:2207.12994, 2022 - arxiv.org
Product retrieval is of great importance in the ecommerce domain. This paper introduces our
1st-place solution in eBay eProduct Visual Search Challenge (FGVC9), which is featured for …

Results and findings of the 2021 Image Similarity Challenge

Z Papakipos, G Tolias, T Jenicek… - NeurIPS 2021 …, 2022 - proceedings.mlr.press
Abstract The 2021 Image Similarity Challenge introduced a dataset to serve as a benchmark
to evaluate image copy detection methods. There were 200 participants to the competition …

[PDF][PDF] Self-Supervised Video Copy Localization with Regional Token Representation: Supplementary Material

M Lu, Y Lu, S Nie, X Yang, X Zhang - ecva.net
In Section Comparison with Supervised Training of the main text, we compare our self-
supervised model (Ours-ssl) with its supervised counterpart (Ours-sup). In this section, we …