Abstract: The disclosed technology is generally directed to identifying media documents embedded within other media documents. In one example of the technology, source fingerprints are generated from input images using a source machine-learning model. The input images are derived from the media documents. Target fingerprints are generated from the input images using a target machine-learning model. The source machine-learning model includes a first neural network. The target machine-learning model includes a second neural network that is different from the first neural network. The source machine-learning model was trained in parallel with the target machine-learning model. Candidate media-document pairs from the media documents are determined based on the source fingerprints and the target fingerprints. Each candidate media-document pair includes a media document that is a candidate for being embedded in another media document.