In this paper we reproduce experimental results presented in our earlier work titled "Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies" that was presented in the course of the 29th ACM International Conference on Multimedia. The paper aims at verifying the soundness of our prior results and helping others understand our software framework. We present artifacts that help reproduce results that were included in our earlier work. Specifically, this paper contains the technical details of the package, including dataset preparation, source code structure and experimental environment. Using the artifacts we show that our results are reproducible. We invite everyone to use our software framework going beyond reproducibility efforts.

Reproducibility Companion Paper: Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies

Deepfake video detection is very challenging due to the hyper-realistic synthesis of frame data. The key is learning discriminative representations to capture fine-grained spatiotemporal cues. Inspired by that, this paper proposes a deepfake video detector learning approach with spatiotemporal predictive representation learning. The detector cascades a short-term transformer-based encoder, a long-term ConvGRU-based aggregator and a SVM-based binary classifier. The encoder and aggregator jointly serve as the backbone and are pretrained in a self-supervised manner. Specially, the encoder is pretrained with a 3D masked autoencoder (3D-MAE) to extract general short-term semantic features, while the aggregator is pretrained with a memory-augmented feature predictor to turn short-term semantic features into long-term context features. In this way, the extracted features can simultaneously describe the latent patterns of videos across frames spatially and temporally in a unified way. Finally, the classifier is trained to classify the context features along with the fine-tuning of the encoder and aggregator, distinguishing fake videos from real ones. Extensive experiments on popular benchmarks clearly demonstrate that the proposed approach significantly outperforms 25 state-of-the-arts, with good generalization ability across datasets.

ACMMM 2022 Track Reproducibility Submissions

Reproducibility Companion Paper: Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies

Spatiotemporal Predictive Representation Learning for Deepfake Video Detection