Upload folder using huggingface_hub

Embeddings/Breakfast_pe-l14.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75733d8a46f4caf1b56efab4eb74742073501755642bb2ce8256adf6269c900f
+size 531724644

Embeddings/HMDB_pe-l14.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3269a832dd456269ade54f386d0a7b7c995055c5f3d9ba45471e3941341864de
+size 337593045

Embeddings/UCF101_pe-l14.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a111cfedd079503dbf06a52963d335c7635725f605b21fd038f606737a0a8d97
+size 560632271

Models/checkpoint_pe-l14_Breakfast.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc101d9b63a6fe6c26949262d1a0d8739bc9590d1b93add1876c80980f1b6708
+size 832157551

Models/checkpoint_pe-l14_HMDB.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14276a1cd5f6b6852e1bd8e65889a8610ba6d90f4b131f282c859ceed1896563
+size 421220125

Models/checkpoint_pe-l14_UCF101.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c4b31f3316c8eb2af7d72f72e456e0bacb072cda6a79a8c97801c7a263fc1e
+size 751733296

README.md

@@ -1,9 +1,3 @@
----
-license: apache-2.0
-language:
-- en
-pipeline_tag: video-classification
----
 # MoTIF — Concepts in Motion
 
 [**Read the Paper (arXiv)**](https://arxiv.org/pdf/2509.20899)
@@ -73,7 +67,9 @@ Adjust hyperparameters in the script or via CLI flags (if exposed).
 
 ## Pretrained Checkpoints
 
-Pretrained MoTIF checkpoints will be uploaded soon. We will publish them under the repository “Releases” page and mirror links here. In the meantime, you can train your own models following the steps above and save checkpoints in `Models/`.
+Pre-trained MoTIF checkpoints for all model variants are available on [Hugging Face](https://huggingface.co/P4ddyki/MoTIF/tree/main). The checkpoints include models trained on Breakfast, HMDB-51, and UCF-101 datasets with PE-L/14 backbone. We will upload soon additional checkpoints.
+
+To use a pre-trained checkpoint, download it from the Hugging Face repository and place it in the `Models/` directory. The notebook `MoTIF.ipynb` will automatically load the appropriate checkpoint based on the dataset and backbone you specify.
 
 ---
 

index.html

@@ -166,6 +166,7 @@
         <div class="cta">
         <a class="btn primary" href="https://arxiv.org/abs/2509.20899" target="_blank" rel="noopener">Paper</a>
         <a class="btn" href="https://github.com/patrick-knab/MoTIF" target="_blank" rel="noopener">Code</a>
+        <a class="btn" href="https://huggingface.co/P4ddyki/MoTIF/tree/main" target="_blank" rel="noopener">Checkpoints</a>
         <a class="btn" href="#video">Demo</a>
       </div>
 
@@ -320,6 +321,7 @@
           </tbody>
         </table>
         <p class="muted"><small>¹ Results from literature. Bold indicates best performance, underlined indicates second best.</small></p>
+        <p style="margin-top: 16px;">Pre-trained checkpoints for all MoTIF models are available at <a href="https://huggingface.co/P4ddyki/MoTIF/tree/main" target="_blank" rel="noopener">Hugging Face</a>.</p>
       </section>
 
       <section id="bibtex" class="panel section">