Feature Extraction
Transformers
Safetensors
prism
video
representation-learning
view-invariant
cross-view
egocentric
egoexo4d
emnlp2026
custom_code
Instructions to use litcoderr/prism with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use litcoderr/prism with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="litcoderr/prism", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("litcoderr/prism", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Mark citation as TODO until proceedings are published
Browse files
README.md
CHANGED
|
@@ -112,15 +112,7 @@ captions, which most datasets do not ship.
|
|
| 112 |
|
| 113 |
## Citation
|
| 114 |
|
| 115 |
-
|
| 116 |
-
@inproceedings{chee2026prism,
|
| 117 |
-
title = {{PRISM}: Predictive Recomposition via Semantic Latent Decomposition
|
| 118 |
-
for View-invariant Video Representation Learning},
|
| 119 |
-
author = {Chee, Youngchae and Lee, Hosu and Park, Sungjune and Kim, Junho and Ro, Yong Man},
|
| 120 |
-
booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
|
| 121 |
-
year = {2026}
|
| 122 |
-
}
|
| 123 |
-
```
|
| 124 |
|
| 125 |
MIT licensed. The frozen backbones keep their own licenses.
|
| 126 |
|
|
|
|
| 112 |
|
| 113 |
## Citation
|
| 114 |
|
| 115 |
+
- [ ] TODO: Add citation once published.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
|
| 117 |
MIT licensed. The frozen backbones keep their own licenses.
|
| 118 |
|