README.md

---
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}
}
```