|
Download README.md from malper/learning-interactions-summarization: direct link, hf CLI and curl.
- Browser
- Download file 2.39 kB
-
https://huggingface.co/malper/learning-interactions-summarization/resolve/main/README.md
- Command line
-
hf download hf://malper/learning-interactions-summarization/README.md
-
curl -L -o README.md https://huggingface.co/malper/learning-interactions-summarization/resolve/main/README.md
2.39 kB
| license: apache-2.0 | |
| base_model: t5-base | |
| tags: | |
| - summarization | |
| - t5 | |
| # HHI caption summarization model | |
| This is the summarization model from **"Learning Human-Human Interactions in Images from Weak Textual Supervision" (ICCV 2023)**: a [T5-base](https://huggingface.co/t5-base) model fine-tuned to summarize captions into short human-human interaction (HHI) descriptions. It is used to generate the pseudo-labels (pHHI) for the Who's Waldo dataset used to train the main HHI understanding model. | |
| - **Paper:** [arXiv:2304.14104](https://arxiv.org/abs/2304.14104) | |
| - **Code:** [github.com/tau-vailab/learning-interactions](https://github.com/tau-vailab/learning-interactions) | |
| - **Project page:** https://learning-interactions.github.io/ | |
| ## Training data | |
| Fine-tuned on synthetic caption data (`synthetic_captions.csv`, available in the [GitHub repo](https://github.com/tau-vailab/learning-interactions/blob/main/data/synthetic_captions.csv)), mapping full captions to their corresponding HHI descriptions. | |
| ## Usage | |
| Can be loaded directly with `transformers`: | |
| ```python | |
| from transformers import pipeline | |
| pipe = pipeline('summarization', model='malper/learning-interactions-summarization', device=0) | |
| pipe('summarize: ' + caption) | |
| ``` | |
| Or used with the pseudo-labeling code in the repo above (`pseudo-labeling/create_pseudolabels.py`, pass via `-m malper/learning-interactions-summarization` or after downloading locally with `hf download malper/learning-interactions-summarization --local-dir output/summarization_model`). | |
| ## Training hyperparameters | |
| - learning_rate: 5e-05 | |
| - train_batch_size: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 3.0 | |
| ### Framework versions | |
| - Transformers 4.18.0 | |
| - PyTorch 1.13.0a0+d0d6b1f | |
| - Datasets 2.8.0 | |
| - Tokenizers 0.12.1 | |
| ## Context | |
| This is research code from 2023, prior to the widespread availability of general-purpose vision-language models (VLMs). It is provided as-is for reproducibility of the paper's results. | |
| ## Citation | |
| ```bibtex | |
| @InProceedings{alper2023learning, | |
| author = {Morris Alper and Hadar Averbuch-Elor}, | |
| title = {Learning Human-Human Interactions in Images from Weak Textual Supervision}, | |
| booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, | |
| year = {2023} | |
| } | |
| ``` | |