Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Swell-and-Shrink: Decomposing Image Captioning by Transformation and Summarization
Authors: Hanzhang Wang, Hanli Wang, Kaisheng Xu
IJCAI 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments demonstrate the effectiveness of the proposed method. |
| Researcher Affiliation | Academia | Hanzhang Wang , Hanli Wang , Kaisheng Xu Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China |
| Pseudocode | No | No pseudocode or clearly labeled algorithm blocks were found in the paper. |
| Open Source Code | No | The paper does not provide an explicit statement about open-sourcing code or a link to a code repository. |
| Open Datasets | Yes | The proposed method is evaluated on the benchmark dataset MSCOCO [Lin et al., 2014] |
| Dataset Splits | Yes | We follow the widely adopted train/val/test split as in [Karpathy and Fei-Fei, 2015], i.e., 5000 images for both validation and testing, and the rest for training. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments (e.g., GPU/CPU models, memory, or cloud instance types). |
| Software Dependencies | No | The paper mentions software components like Faster R-CNN, VGG16, and ADAM optimizer but does not specify their version numbers or other crucial software dependencies required for replication. |
| Experiment Setup | Yes | In the language model, the number of hidden units and the number of factors in each LSTM are all set to 512. A gradient will be clipped if its value exceeds 1. The ADAM optimizer is used for training with α = 0.8, β = 0.999 and ϵ = 1 10 8. The initial learning rate is set to 1 10 4 and exponential reduction is used which halves the learning rate every 10 epochs. |