Visual Sentiment Analysis by Attending on Local Image Regions

Authors: Quanzeng You, Hailin Jin, Jiebo Luo

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results suggest that 1) our model is capable of automatically discovering sentimental local regions of given images and 2) it outperforms existing state-of-the-art algorithms to visual sentiment analysis.
Researcher Affiliation Collaboration Quanzeng You Department of Computer Science University of Rochester Rochester, NY 14627 qyou@cs.rochester.edu Hailin Jin Adobe Research 345 Park Avenue San Jose, CA 95110 hljin@adobe.com Jiebo Luo Department of Computer Science University of Rochester Rochester, NY 14627 jluo@cs.rochester.edu
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any links to or statements about the availability of its own source code for the described methodology.
Open Datasets Yes We evaluate the proposed model on the publicly available benchmark dataset visual sentiment ontology (VSO)... 1http://www.ee.columbia.edu/ln/dvmm/vso/download/sentibank.html
Dataset Splits Yes We randomly split them into 80% for training, 10% for testing and 10% for validating.
Hardware Specification No The paper does not specify any hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions using "Caffe" but does not specify its version number or any other software dependencies with version information.
Experiment Setup Yes All the parameters are automatically learned by minimizing the two loss functions over the training split. We use a mini-batch gradient descent algorithm with an adaptive learning rate to optimize the loss functions. After only 2 epochs over the training split, the classification on validating split has been all correct.