MMathisLab · May 15, 2026 · May 4, 2026 · May 4, 2026 · May 7, 2026 · May 7, 2026
diff --git a/deeplabcut/__init__.py b/deeplabcut/__init__.py
@@ -102,6 +102,7 @@
     DownSampleVideo,
     ShortenVideo,
     check_video_integrity,
+    collect_video_paths,
 )
 
 # -----------------------------------------------------------------------------

diff --git a/deeplabcut/compat.py b/deeplabcut/compat.py
@@ -12,7 +12,7 @@
 
 from __future__ import annotations
 
-from collections.abc import Iterable
+from collections.abc import Iterable, Sequence
 from pathlib import Path
 
 import numpy as np
@@ -664,7 +664,7 @@ def return_evaluate_network_data(
 def analyze_videos(
     config: str,
     videos: list[str],
-    videotype: str = "",
+    videotype: str | Sequence[str] | None = None,
     shuffle: int = 1,
     trainingsetindex: int = 0,
     gputouse: str | None = None,
@@ -710,10 +710,14 @@ def analyze_videos(
         A list of strings containing the full paths to videos for analysis or a path to
         the directory, where all the videos with same extension are stored.
 
-    videotype: str, optional, default=""
-        Checks for the extension of the video in case the input to the video is a
-        directory. Only videos with this extension are analyzed. If left unspecified,
-        videos with common extensions ('avi', 'mp4', 'mov', 'mpeg', 'mkv') are kept.
+    videotype : str | Sequence[str] | None, optional, default=None
+        Controls how ``videos`` are filtered, based on file extension.
+        File paths and directory contents are treated differently:
+        - ``None`` (default): file paths are accepted as-is; directories are
+          scanned for files with a recognized video extension.
+        - ``str`` or ``Sequence[str]`` (e.g. ``"mp4"`` or ``["mp4", "avi"]``):
+          both file paths and directory contents are filtered by the given
+          extension(s).
 
     shuffle: int, optional, default=1
         An integer specifying the shuffle index of the training dataset used for
@@ -986,7 +990,7 @@ def create_tracking_dataset(
     config: str,
     videos: list[str],
     track_method: str,
-    videotype: str = "",
+    videotype: str | Sequence[str] | None = None,
     shuffle: int = 1,
     trainingsetindex: int = 0,
     gputouse: int | None = None,
@@ -1015,10 +1019,14 @@ def create_tracking_dataset(
         Specifies the tracker used to generate the pose estimation data. Must be either
         'box', 'skeleton', or 'ellipse'.
 
-    videotype: str, optional, default=""
-        Checks for the extension of the video in case the input to the video is a
-        directory. Only videos with this extension are analyzed. If left unspecified,
-        videos with common extensions ('avi', 'mp4', 'mov', 'mpeg', 'mkv') are kept.
+    videotype : str | Sequence[str] | None, optional, default=None
+        Controls how ``videos`` are filtered, based on file extension.
+        File paths and directory contents are treated differently:
+        - ``None`` (default): file paths are accepted as-is; directories are
+          scanned for files with a recognized video extension.
+        - ``str`` or ``Sequence[str]`` (e.g. ``"mp4"`` or ``["mp4", "avi"]``):
+          both file paths and directory contents are filtered by the given
+          extension(s).
 
     shuffle: int, optional, default=1
         An integer specifying the shuffle index of the training dataset used for
@@ -1408,7 +1416,7 @@ def analyze_time_lapse_frames(
 def convert_detections2tracklets(
     config: str,
     videos: list[str],
-    videotype: str = "",
+    videotype: str | Sequence[str] | None = None,
     shuffle: int = 1,
     trainingsetindex: int = 0,
     overwrite: bool = False,
@@ -1435,10 +1443,14 @@ def convert_detections2tracklets(
         A list of strings containing the full paths to videos for analysis or a path to the directory,
         where all the videos with same extension are stored.
 
-    videotype: string, optional
-        Checks for the extension of the video in case the input to the video is a directory.\n
-        Only videos with this extension are analyzed.
-        If left unspecified, videos with common extensions ('avi', 'mp4', 'mov', 'mpeg', 'mkv') are kept.
+    videotype : str | Sequence[str] | None, optional, default=None
+        Controls how ``videos`` are filtered, based on file extension.
+        File paths and directory contents are treated differently:
+        - ``None`` (default): file paths are accepted as-is; directories are
+          scanned for files with a recognized video extension.
+        - ``str`` or ``Sequence[str]`` (e.g. ``"mp4"`` or ``["mp4", "avi"]``):
+          both file paths and directory contents are filtered by the given
+          extension(s).
 
     shuffle: int, optional
         An integer specifying the shuffle index of the training dataset used for training the network. T

diff --git a/deeplabcut/pose_estimation_pytorch/apis/tracking_dataset.py b/deeplabcut/pose_estimation_pytorch/apis/tracking_dataset.py
@@ -10,6 +10,7 @@
 #
 """Code to create tracking datasets for ReID model training."""
 
+from collections.abc import Sequence
 from pathlib import Path
 
 from tqdm import tqdm
@@ -24,6 +25,7 @@
 from deeplabcut.pose_estimation_pytorch.apis.videos import VideoIterator
 from deeplabcut.pose_estimation_pytorch.task import Task
 from deeplabcut.pose_tracking_pytorch import create_triplets_dataset
+from deeplabcut.utils.auxfun_videos import collect_video_paths
 
 
 def build_feature_extraction_runner(
@@ -127,7 +129,7 @@ def create_tracking_dataset(
     config: str,
     videos: list[str] | list[Path],
     track_method: str,
-    videotype: str = "",
+    videotype: str | Sequence[str] | None = None,
     shuffle: int = 1,
     trainingsetindex: int = 0,
     destfolder: str | None = None,
@@ -147,10 +149,13 @@ def create_tracking_dataset(
             the videos with same extension are stored.
         track_method: Specifies the tracker used to generate the pose estimation data.
             Must be either 'box', 'skeleton', or 'ellipse'.
-        videotype: Checks for the extension of the video in case the input to the video
-            is a directory. Only videos with this extension are analyzed. If left
-            unspecified, keeps videos with extensions ('avi', 'mp4', 'mov', 'mpeg',
-            'mkv').
+        videotype: Controls how ``videos`` are filtered, based on file extension.
+            File paths and directory contents are treated differently:
+            - ``None`` (default): file paths are accepted as-is; directories are
+              scanned for files with a recognized video extension.
+            - ``str`` or ``Sequence[str]`` (e.g. ``"mp4"`` or ``["mp4", "avi"]``):
+              both file paths and directory contents are filtered by the given
+              extension(s).
         shuffle: An integer specifying the shuffle index of the training dataset used
             for training the network.
         trainingsetindex: Integer specifying which TrainingsetFraction to use.
@@ -240,7 +245,7 @@ def create_tracking_dataset(
         modelprefix=modelprefix,
     )
 
-    videos = utils.list_videos_in_folder(videos, videotype)
+    videos = collect_video_paths(videos, extensions=videotype)
     for video_path in videos:
         print(f"Loading {video_path}")
         video = VideoIterator(video_path, cropping=cropping)

diff --git a/deeplabcut/pose_estimation_pytorch/apis/tracklets.py b/deeplabcut/pose_estimation_pytorch/apis/tracklets.py
@@ -11,6 +11,7 @@
 import os
 import pickle
 import warnings
+from collections.abc import Sequence
 from pathlib import Path
 
 import numpy as np
@@ -26,16 +27,16 @@
 from deeplabcut.core.inferenceutils import Assembly
 from deeplabcut.pose_estimation_pytorch.apis.utils import (
     get_scorer_name,
-    list_videos_in_folder,
     parse_snapshot_index_for_analysis,
 )
 from deeplabcut.pose_estimation_pytorch.data.dlcloader import DLCLoader
+from deeplabcut.utils.auxfun_videos import collect_video_paths
 
 
 def convert_detections2tracklets(
     config: str,
     videos: str | list[str],
-    videotype: str | None = None,
+    videotype: str | Sequence[str] | None = None,
     shuffle: int = 1,
     trainingsetindex: int = 0,
     overwrite: bool = False,
@@ -124,9 +125,10 @@ def convert_detections2tracklets(
         modelprefix=modelprefix,
     )
 
-    videos = list_videos_in_folder(videos, videotype)
+    paths_input = videos
+    videos = collect_video_paths(videos, extensions=videotype)
     if len(videos) == 0:
-        print(f"No videos were found in {videos}")
+        print(f"No videos were found in {paths_input}")
         return
 
     for video in videos:

diff --git a/deeplabcut/pose_estimation_pytorch/apis/utils.py b/deeplabcut/pose_estimation_pytorch/apis/utils.py
@@ -11,8 +11,7 @@
 from __future__ import annotations
 
 import logging
-import random
-from collections.abc import Callable
+from collections.abc import Callable, Sequence
 from pathlib import Path
 
 import albumentations as A
@@ -65,7 +64,9 @@
 )
 from deeplabcut.pose_estimation_pytorch.task import Task
 from deeplabcut.pose_estimation_pytorch.utils import resolve_device
-from deeplabcut.utils import auxfun_videos, auxiliaryfunctions
+from deeplabcut.utils import auxiliaryfunctions
+from deeplabcut.utils.auxfun_videos import SUPPORTED_VIDEOS, collect_video_paths
+from deeplabcut.utils.deprecation import deprecated
 
 
 def parse_snapshot_index_for_analysis(
@@ -293,49 +294,17 @@ def get_scorer_name(
     return f"DLC_{name}_{task}{date}shuffle{shuffle}_{snapshot_uid}"
 
 
+@deprecated(replacement="deeplabcut.collect_video_paths", since="3.0.0")
 def list_videos_in_folder(
     data_path: str | Path | list[str | Path],
-    video_type: str | None = None,
+    video_type: str | Sequence[str] | None = SUPPORTED_VIDEOS,
     shuffle: bool = False,
 ) -> list[Path]:
-    """
-    Args:
-        data_path: Path or list of paths to folders containing videos, or individual
-            video files. Can be a mix of directories and files.
-        video_type: The type of video to filter for (e.g., "mp4", ".mp4"). If None,
-            all supported video types are included.
-        shuffle: Whether to shuffle the order of videos. If False, videos are returned
-            in sorted order for deterministic behavior.
-
-    Returns:
-        The paths of videos to analyze. Duplicate paths are removed.
-
-    Raises:
-        FileNotFoundError: If any path in data_path does not exist.
-    """
-    if isinstance(data_path, (str, Path)):
-        data_path = [data_path]
-
-    if not video_type:
-        video_suffixes = {f".{ext.lower()}" for ext in auxfun_videos.SUPPORTED_VIDEOS}
-    else:
-        video_suffixes = {f".{video_type.lstrip('.').lower()}"}
-
-    videos = []
-    for path in map(Path, data_path):
-        if not path.exists():
-            raise FileNotFoundError(f"Could not find: {path}. Check access rights.")
-
-        if path.is_dir():
-            videos.extend(f for f in path.iterdir() if f.is_file() and f.suffix.lower() in video_suffixes)
-        elif path.is_file() and path.suffix.lower() in video_suffixes:
-            videos.append(path)
-
-    # Resolve video paths and remove duplicates
-    unique_videos = list(dict.fromkeys(v.resolve() for v in videos))
-    if shuffle:
-        random.shuffle(unique_videos)
-    return unique_videos
+    return collect_video_paths(
+        data_path=data_path,
+        extensions=video_type,
+        shuffle=shuffle,
+    )
 
 
 def ensure_multianimal_df_format(df_predictions: pd.DataFrame) -> pd.DataFrame:

diff --git a/deeplabcut/pose_estimation_pytorch/apis/videos.py b/deeplabcut/pose_estimation_pytorch/apis/videos.py
@@ -14,6 +14,7 @@
 import logging
 import pickle
 import time
+from collections.abc import Sequence
 from pathlib import Path
 from typing import Any
 
@@ -44,6 +45,7 @@
 from deeplabcut.pose_estimation_pytorch.task import Task
 from deeplabcut.refine_training_dataset.stitch import stitch_tracklets
 from deeplabcut.utils import VideoReader, auxiliaryfunctions
+from deeplabcut.utils.auxfun_videos import collect_video_paths
 
 
 class VideoIterator(VideoReader):
@@ -242,7 +244,7 @@ def video_inference(
 def analyze_videos(
     config: str,
     videos: str | list[str],
-    videotype: str | None = None,
+    videotype: str | Sequence[str] | None = None,
     shuffle: int = 1,
     trainingsetindex: int = 0,
     save_as_csv: bool = False,
@@ -282,9 +284,13 @@ def analyze_videos(
         videos: a str (or list of strings) containing the full paths to videos for
             analysis or a path to the directory, where all the videos with same
             extension are stored.
-        videotype: checks for the extension of the video in case the input to the video
-            is a directory. Only videos with this extension are analyzed. If left
-            unspecified, keeps videos with extensions ('avi', 'mp4', 'mov', 'mpeg', 'mkv').
+        videotype: Controls how ``videos`` are filtered, based on file extension.
+            File paths and directory contents are treated differently:
+            - ``None`` (default): file paths are accepted as-is; directories are
+              scanned for files with a recognized video extension.
+            - ``str`` or ``Sequence[str]`` (e.g. ``"mp4"`` or ``["mp4", "avi"]``):
+              both file paths and directory contents are filtered by the given
+              extension(s).
         shuffle: An integer specifying the shuffle index of the training dataset used for
             training the network.
         trainingsetindex: Integer specifying which TrainingsetFraction to use.
@@ -540,7 +546,7 @@ def analyze_videos(
     print(f"Using scorer: {dlc_scorer}")
 
     # Reading video and init variables
-    videos = utils.list_videos_in_folder(videos, videotype, shuffle=in_random_order)
+    videos = collect_video_paths(videos, extensions=videotype, shuffle=in_random_order)
     h5_files_created = False  # Track if any .h5 files were created
 
     for video in videos:

diff --git a/deeplabcut/pose_estimation_tensorflow/modelzoo/api/superanimal_inference.py b/deeplabcut/pose_estimation_tensorflow/modelzoo/api/superanimal_inference.py
@@ -14,6 +14,7 @@
 import pickle
 import time
 import warnings
+from collections.abc import Sequence
 from pathlib import Path
 
 import imgaug.augmenters as iaa
@@ -26,7 +27,7 @@
 from deeplabcut.pose_estimation_tensorflow.core import predict as single_predict
 from deeplabcut.pose_estimation_tensorflow.core import predict_multianimal as predict
 from deeplabcut.utils import auxiliaryfunctions
-from deeplabcut.utils.auxfun_videos import VideoWriter
+from deeplabcut.utils.auxfun_videos import VideoWriter, collect_video_paths
 
 warnings.simplefilter("ignore", category=RuntimeWarning)
 
@@ -247,7 +248,7 @@ def video_inference(
     project_name,
     model_name,
     scale_list=None,
-    videotype="avi",
+    videotype: str | Sequence[str] | None = None,
     destfolder=None,
     batchsize=1,
     robust_nframes=False,
@@ -306,7 +307,7 @@ def video_inference(
 
     sess, inputs, outputs = single_predict.setup_pose_prediction(test_cfg, allow_growth=allow_growth)
     DLCscorer = "DLC_" + Path(test_cfg["init_weights"]).stem
-    videos = auxiliaryfunctions.get_list_of_videos(videos, videotype)
+    videos = collect_video_paths(videos, extensions=videotype)
 
     datafiles = []
     for video in videos: