Add model card and pipeline tag for VisCoP

README.md

@@ -0,0 +1,88 @@
+---
+pipeline_tag: video-text-to-text
+---
+
+# VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models
+
+This repository contains the model checkpoints for **VisCoP** (Vision Contextualized Probing), a parameter-efficient adaptation framework that augments Vision-Language Models (VLMs) with a compact set of learnable visual probes for robust domain adaptation under distribution shifts.
+
+For more details, please refer to:
+* **Paper:** [VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models](https://huggingface.co/papers/2510.13808)
+* **GitHub Repository:** [dominickrei/VisCoP](https://github.com/dominickrei/VisCoP)
+
+---
+
+## ⚙️ Installation
+
+To set up the environment, clone the official repository and install the dependencies:
+
+```shell
+git clone https://github.com/dominickrei/VisCoP.git
+cd VisCoP
+pip install -r requirements.txt
+pip install flash-attn --no-build-isolation
+```
+
+## 💻 Inference
+
+You can run video-based inference using the following Python script:
+
+```python
+from viscop import model_init, mm_infer
+from viscop.mm_utils import load_video
+
+## Load model
+model_path = 'dreilly/viscop-models'  # Update with your local path or specific checkpoint subfolder
+
+model, processor = model_init(
+    model_path=model_path,
+    device_map={"": "cuda"}
+)
+
+## Load video
+video_path = './assets/ego_cut_carrot.mp4'
+
+frames, timestamps = load_video(video_path, fps=1, max_frames=180)
+
+## Create conversation
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "video", "timestamps": timestamps, "num_frames": len(frames)},
+            {"type": "text", "text": "What vegetable is the person cutting in the video?"},
+        ]
+    }
+]
+
+## Perform inference
+inputs = processor(
+    images=[frames],
+    text=conversation,
+    merge_size=2,
+    return_tensors="pt",
+)
+
+prediction = mm_infer(
+    inputs,
+    model=model,
+    tokenizer=processor.tokenizer,
+    do_sample=False,
+    modal='video'
+)
+
+print(prediction)
+```
+
+## Citation
+
+If you find this work helpful, please consider citing our paper:
+
+```bibtex
+@inproceedings{reilly2026viscop,
+  title     = {VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models},
+  author    = {Dominick Reilly and Manish Kumar Govind and Le Xue and Srijan Das},
+  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
+  year      = {2026}
+}
+```