Mining User Interests from Personal Photos

Authors: Pengtao Xie, Yulong Pei, Yuan Xie, Eric Xing

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on 180K Flickr photos demonstrate the effectiveness of our model.
Researcher Affiliation Academia Pengtao Xie, Yulong Pei, Yuan Xie and Eric Xing {pengtaox,epxing}@cs.cmu.edu,{yulongp, yxie1}@andrew.cmu.edu School of Computer Science, Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213
Pseudocode No The paper describes a generative process and mathematical derivations but does not include a block explicitly labeled 'Pseudocode' or 'Algorithm'.
Open Source Code No The paper does not provide any information or link indicating that its source code is open or publicly available.
Open Datasets No The paper states 'We crawl 183723 personal photos from 227 Flickr users' but does not provide concrete access information (link, DOI, specific citation with author/year for a dataset, or repository) for this collected dataset, nor does it refer to a standard, publicly available Flickr dataset in a way that allows access.
Dataset Splits No The paper mentions assembling a 'test set' of 22700 images, but does not specify the splits for training, validation, and testing needed to reproduce the experiment.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper mentions methods like SLIC, SIFT, and BOW features, but it does not specify any software dependencies with version numbers (e.g., Python version, library versions like TensorFlow, PyTorch, scikit-learn).
Experiment Setup Yes We set the number of background themes to 100, the number of user-interested themes to 1000, the number of semantic regions to 1500 and the number of visual words to 500. The tradeoff parameters λ(δ), λ(t), λ(o), λ(w) are all set to 1. The model is initialized randomly.