diff --git a/torchvision/tv_tensors/_bounding_boxes.py b/torchvision/tv_tensors/_bounding_boxes.py
index 56e77c2a85e..ea02fa3dc7b 100644
--- a/torchvision/tv_tensors/_bounding_boxes.py
+++ b/torchvision/tv_tensors/_bounding_boxes.py
@@ -25,7 +25,7 @@ class BoundingBoxFormat(Enum):
 
 
 class BoundingBoxes(TVTensor):
-    """:class:`torch.Tensor` subclass for bounding boxes.
+    """:class:`torch.Tensor` subclass for bounding boxes with shape ``[N, 4]``.
 
     .. note::
         There should be only one :class:`~torchvision.tv_tensors.BoundingBoxes`
diff --git a/torchvision/tv_tensors/_image.py b/torchvision/tv_tensors/_image.py
index c2f82c8d0df..2a0a2ec7209 100644
--- a/torchvision/tv_tensors/_image.py
+++ b/torchvision/tv_tensors/_image.py
@@ -9,7 +9,7 @@
 
 
 class Image(TVTensor):
-    """:class:`torch.Tensor` subclass for images.
+    """:class:`torch.Tensor` subclass for images with shape ``[..., C, H, W]``.
 
     .. note::
 
diff --git a/torchvision/tv_tensors/_mask.py b/torchvision/tv_tensors/_mask.py
index a8f6f4d62cb..ef9d96159fb 100644
--- a/torchvision/tv_tensors/_mask.py
+++ b/torchvision/tv_tensors/_mask.py
@@ -9,7 +9,7 @@
 
 
 class Mask(TVTensor):
-    """:class:`torch.Tensor` subclass for segmentation and detection masks.
+    """:class:`torch.Tensor` subclass for segmentation and detection masks with shape ``[..., H, W]``.
 
     Args:
         data (tensor-like, PIL.Image.Image): Any data that can be turned into a tensor with :func:`torch.as_tensor` as
diff --git a/torchvision/tv_tensors/_video.py b/torchvision/tv_tensors/_video.py
index a0466b001ee..aa923e781ef 100644
--- a/torchvision/tv_tensors/_video.py
+++ b/torchvision/tv_tensors/_video.py
@@ -8,7 +8,7 @@
 
 
 class Video(TVTensor):
-    """:class:`torch.Tensor` subclass for videos.
+    """:class:`torch.Tensor` subclass for videos with shape ``[..., T, C, H, W]``.
 
     Args:
         data (tensor-like): Any data that can be turned into a tensor with :func:`torch.as_tensor`.