Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Video Prediction with Appearance and Motion Conditions
Authors: Yunseok Jang, Gunhee Kim, Yale Song
ICML 2018 | Venue PDF | 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 classi๏ฌer 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). |