Paraphrasing Is All You Need for Novel Object Captioning
Authors: Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan, Russ R. Salakhutdinov, Louis-Philippe Morency, Frank Wang
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In the experiments, we not only show that our P2C achieves state-of-the-art performances on nocaps and COCO Caption datasets, we also verify the effectiveness and flexibility of our learning framework by replacing language and cross-modality association models for NOC. |
| Researcher Affiliation | Collaboration | 1UCLA 2Carnegie Mellon University 3National Taiwan University 4NVIDIA |
| Pseudocode | No | The paper describes its methodology in detail with text and diagrams (Figures 1 and 2) but does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks or structured code-like formatting. |
| Open Source Code | Yes | Implementation details and code are available in the supplementary materials. |
| Open Datasets | Yes | The training data for the nocaps benchmark comprises the Open Images V4 [37] object detection training set (1.7M images annotated with bounding boxes for 600 object classes), plus the image-caption pairs from the COCO Captions 2017 [2] training set (0.5M image-caption pairs containing 80 object classes). |
| Dataset Splits | Yes | We evaluate our model on the validation and test set of nocaps, which comprises 4500 and 10600 images from the Open Images validation and test sets, respectively. |
| Hardware Specification | No | The main body of the paper does not specify the exact hardware used (e.g., specific GPU models, CPU types) for running experiments. While the checklist indicates this information is in supplementary materials, it is not present in the primary text. |
| Software Dependencies | No | The paper mentions using models like BERT and CLIP and refers to 'Implementation details' in the supplementary materials, but it does not specify software dependencies like programming languages, libraries, or frameworks with their exact version numbers within the main text. |
| Experiment Setup | No | The paper states, 'Due to page limits, hyperparameters and other training details can be found in Appendix B.' This indicates that detailed experimental setup information, such as specific hyperparameter values, is not present in the main body of the paper. |