Video Prediction with Appearance and Motion Conditions

Authors: Yunseok Jang, Gunhee Kim, Yale Song

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our model using facial expression and human action datasets and report favorable results compared to existing methods.
Researcher Affiliation Collaboration Yunseok Jang 1 2 Gunhee Kim 2 Yale Song 3 [...] 1University of Michigan, Ann Arbor 2Seoul National University 3Microsoft AI & Research.
Pseudocode Yes Algorithm 1 summarizes how we train our model.
Open Source Code Yes The code is available at http://vision.snu.ac.kr/projects/amc-gan.
Open Datasets Yes We evaluate our approach on the MUG facial expression dataset (Aifanti et al., 2010) and the NATOPS human action dataset (Song et al., 2011).
Dataset Splits Yes We train the classifier on real training data, using roughly 10% for validation, and test it on generated videos from different methods.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers, such as programming languages, libraries, or frameworks with their respective versions.
Experiment Setup Yes We use the ADAM optimizer (Kingma & Ba, 2015) with learning rate 2e-4. For the cross entropy losses, we adopt the label smoothing trick (Salimans et al., 2016) with a weight decay of 1e-5 per mini-batch (Arjovsky & Bottou, 2017).