MLAdaptiveIntelligence
/

PRIMA

@@ -1,11 +1,10 @@
 ---
-license: apache-2.0
 tags:
 - computer_vision
 - animal_pose_and_shape_estimation
-- deeplabcut
 pipeline_tag: image-to-3d
 ---
 # MODEL CARD:
@@ -33,7 +32,7 @@ download_huggingface_model("prima_animal_model_pytorch", model_dir)
 and ecology.
 • Not suitable as a zero-shot model for applications that require high shape and pose precision, but can be further optimized with 2D keypoint
-annotations or from Deeplabcut_Superanimal to improve accuracy. Also not suitable for videos that look dramatically different from those
 we show in the paper.
 ## Metrics
@@ -87,5 +86,4 @@ In: ICCV. pp. 9099–9109 (2023)
 Animal pose and shape estimation using a family-aware transformer. In: CVPR. pp.
 17486–17496 (2025)
 3. Ye, S., Filippova, A., Lauer, J., Schneider, S., Vidal, M., Qiu, T., Mathis, A.,
-Mathis, M.W.: Superanimal pretrained pose estimation models for behavioral anal-
-ysis. Nature communications 15(1), 5165 (2024)

 ---
 tags:
 - computer_vision
 - animal_pose_and_shape_estimation
+- DeepLabCut
 pipeline_tag: image-to-3d
+license: mit
 ---
 # MODEL CARD:
 and ecology.
 • Not suitable as a zero-shot model for applications that require high shape and pose precision, but can be further optimized with 2D keypoint
+annotations or from SuperAnimal to improve accuracy. Also, it is not suitable for videos that look dramatically different from those
 we show in the paper.
 ## Metrics
 Animal pose and shape estimation using a family-aware transformer. In: CVPR. pp.
 17486–17496 (2025)
 3. Ye, S., Filippova, A., Lauer, J., Schneider, S., Vidal, M., Qiu, T., Mathis, A.,
+Mathis, M.W.: Superanimal pretrained pose estimation models for behavioral analysis. Nature communications 15(1), 5165 (2024)