Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
Authors: Michael Ryoo, Brandon Rothrock, Charles Fleming, Hyun Jong Yang
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We experimentally confirm that the paradigm of inverse super resolution is able to benefit activity recognition from extreme low-resolution videos. |
| Researcher Affiliation | Collaboration | Michael S. Ryoo,1,2 Brandon Rothrock,3 Charles Fleming,4 Hyun Jong Yang2,5 1Indiana University, Bloomington, IN 2Ego Vid Inc., Ulsan, South Korea 3Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA 4Xi an Jiaotong-Liverpool University, Suzhou, China 5Ulsan National Institute of Science and Technology, Ulsan, South Korea |
| Pseudocode | No | The paper describes methods in text and mathematical formulations but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not state that the source code for the described methodology is publicly available, nor does it provide any link to a code repository. |
| Open Datasets | Yes | We selected three public datasets and resized them to obtain low resolution (e.g., 16x12) videos. HMDB dataset (Kuehne et al. 2011) is a dataset popularly used for video classification. ... Dog Centric dataset (Iwashita et al. 2014) and JPL-Interaction dataset (Ryoo and Matthies 2013) are the first-person video datasets taken with wearable/robot cameras. |
| Dataset Splits | Yes | A is a validation set with activity videos, being used to measure the empirical similarity between two classification functions. In the case of JPL-Interaction dataset with robot videos, 12-fold leave-one-set-out cross validation was used. |
| Hardware Specification | No | The paper does not provide specific hardware details (such as GPU or CPU models, or memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper mentions software components and methods used (e.g., SVMs, CNNs, MCMC) but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | No | The paper describes general experimental settings like dataset resolutions, feature types, classifier types, and data augmentation strategies, but it does not provide specific hyperparameters such as learning rates, batch sizes, or explicit optimizer settings. |