Unsupervised learning of object structure and dynamics from videos
Authors: Matthias Minderer, Chen Sun, Ruben Villegas, Forrester Cole, Kevin P. Murphy, Honglak Lee
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the Deep Mind Control Suite. The spatially structured representation outperforms unstructured representations on a range of motion-related tasks such as object tracking, action recognition and reward prediction. |
| Researcher Affiliation | Industry | Matthias Minderer Chen Sun Ruben Villegas Forrester Cole Kevin Murphy Honglak Lee Google Research {mjlm, chensun, rubville, fcole, kpmurphy, honglak}@google.com |
| Pseudocode | No | The paper describes the architecture and training process in detail, but it does not include any formal pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code or a direct link to a code repository for the methodology described. |
| Open Datasets | Yes | We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the Deep Mind Control Suite. The Basketball dataset contains 107,146 training and 13,845 test sequences. The Human3.6 dataset [11] contains video sequences of human actors performing various actions. We use subjects S1, S5, S6, S7, and S9 for training (600 videos), and subjects S9 and S11 for evaluation (239 videos). |
| Dataset Splits | No | The paper specifies training and test/evaluation splits for the datasets, but it does not explicitly mention a separate validation set size or split. |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions certain models and architectures (e.g., VRNN, CNN-VRNN, SVG), but it does not provide specific software names with version numbers for implementation dependencies (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | No | The paper states: "See Section S1 for implementation details, including a list of hyperparameters and tuning ranges (Table S1)." While it refers to these details, they are not present directly in the main text of the paper. |