Upload folder using huggingface_hub
Browse files- README.md +43 -0
- cc_ft.ckpt +3 -0
README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- pytorch-lightning
|
| 5 |
+
- image-captioning
|
| 6 |
+
- vision
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# CLIPCap fine-tuned for Human-Human Interaction captioning (cc_ft)
|
| 10 |
+
|
| 11 |
+
This is the best-performing checkpoint from **"Learning Human-Human Interactions in Images from Weak Textual Supervision" (ICCV 2023)**: a [CLIPCap](https://github.com/rmokady/CLIP_prefix_caption) model fine-tuned on pseudo-labels (pHHI) for describing human-human interactions (HHI) in images.
|
| 12 |
+
|
| 13 |
+
- **Paper:** [arXiv:2304.14104](https://arxiv.org/abs/2304.14104)
|
| 14 |
+
- **Code:** [github.com/tau-vailab/learning-interactions](https://github.com/tau-vailab/learning-interactions)
|
| 15 |
+
- **Project page:** https://learning-interactions.github.io/
|
| 16 |
+
|
| 17 |
+
Note: this checkpoint has been computed from scratch and may differ slightly from the results reported in the paper due to randomness during training.
|
| 18 |
+
|
| 19 |
+
## Usage
|
| 20 |
+
|
| 21 |
+
This checkpoint is a PyTorch Lightning checkpoint (`cc_ft.ckpt`), intended for use with the inference code in the repo above (`modeling/src/test.py`):
|
| 22 |
+
|
| 23 |
+
```bash
|
| 24 |
+
hf download malper/learning-interactions-cc-ft cc_ft.ckpt --local-dir .
|
| 25 |
+
python src/test.py -d <image_dir> -o <output.json> -c cc_ft.ckpt -cc <clipcap_pretrained_weights>
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
See the [modeling documentation](https://github.com/tau-vailab/learning-interactions/tree/main/modeling) for full details, including the required CLIPCap pretrained MLP mapping network weights.
|
| 29 |
+
|
| 30 |
+
## Context
|
| 31 |
+
|
| 32 |
+
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.
|
| 33 |
+
|
| 34 |
+
## Citation
|
| 35 |
+
|
| 36 |
+
```bibtex
|
| 37 |
+
@InProceedings{alper2023learning,
|
| 38 |
+
author = {Morris Alper and Hadar Averbuch-Elor},
|
| 39 |
+
title = {Learning Human-Human Interactions in Images from Weak Textual Supervision},
|
| 40 |
+
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
|
| 41 |
+
year = {2023}
|
| 42 |
+
}
|
| 43 |
+
```
|
cc_ft.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97c5d02189cd8a39d9da027f7b4c85474e2c4bae5c409107b5b944773e8ca8c6
|
| 3 |
+
size 2488951568
|