Exploring Models and Data for Image Question Answering

Authors: Mengye Ren, Ryan Kiros, Richard Zemel

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

Reproducibility Variable Result LLM Response
Research Type Experimental 4 Experimental Results
Researcher Affiliation Academia Mengye Ren1, Ryan Kiros1, Richard S. Zemel1,2 University of Toronto1 Canadian Institute for Advanced Research2 {mren, rkiros, zemel}@cs.toronto.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes We release the complete details of the models at https://github.com/renmengye/ imageqa-public.
Open Datasets Yes COCO-QA dataset can be downloaded at http://www.cs.toronto.edu/ mren/ imageqa/data/cocoqa
Dataset Splits Yes Table 1: COCO-QA question type break-down CATEGORY TRAIN % TEST % OBJECT 54992 69.84% 27206 69.85% NUMBER 5885 7.47% 2755 7.07% COLOR 13059 16.59% 6509 16.71% LOCATION 4800 6.10% 2478 6.36% TOTAL 78736 100.00% 38948 100.00%
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types) used for running its experiments.
Software Dependencies No The paper mentions software like 'Stanford parser', 'Word Net', and 'NLTK software package', but does not provide specific version numbers for these dependencies.
Experiment Setup No The paper does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings.