Video Prediction via Selective Sampling
Authors: Jingwei Xu, Bingbing Ni, Xiaokang Yang
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on diverse challenging datasets demonstrate the effectiveness of proposed video prediction approach, i.e., yielding more diverse proposals and accurate prediction results. |
| Researcher Affiliation | Academia | Jingwei Xu, Bingbing Ni , Xiaokang Yang Mo E Key Lab of Artificial Intelligence, AI Institute SJTU-UCLA Joint Research Center on Machine Perception and Inference, Shanghai Jiao Tong University, Shanghai 200240, China Shanghai Institute for Advanced Communication and Data Science xjwxjw,nibingbing,xkyang@sjtu.edu.cn |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper references open-source codes for *other* models (MCNet, Dr Net, SAVP) in footnote 2, but does not provide concrete access to the source code for its *own* methodology. |
| Open Datasets | Yes | We evaluate our framework (VPSS) on three diverse datasets: Moving Mnist [33], Robot Push [10] and Human3.6M [17], which represent challenges in different aspects. |
| Dataset Splits | No | The paper mentions datasets used for evaluation but does not provide specific training, validation, and test dataset splits (e.g., percentages or sample counts) needed for reproduction. It only states 'different from predicting 10 frames during training, we predict 20 frames to validate the generalization ability.' |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper states 'We implement the proposed framework with Tensorflow library [1]' but does not provide specific version numbers for TensorFlow or any other software dependencies. |
| Experiment Setup | Yes | We pre-train φspl and ψslt for 2 epochs. The curriculum learning is essentially increasing the prediction length by 1 every epoch with initial length of 1. In all experiments we train all our models with the ADAM optimizer [23] and learning rate η = 0.0001, β1 = 0.5, β2 = 0.999. In all experiments we set N = 5 and K = 2. |