diff --git a/demo/Demo_openpose_videos.py b/demo/Demo_openpose_videos.py
new file mode 100644
index 0000000000..c3eec22352
--- /dev/null
+++ b/demo/Demo_openpose_videos.py
@@ -0,0 +1,89 @@
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+import argparse
+import glob
+import multiprocessing as mp
+import os
+import time
+import cv2
+import tqdm
+
+from detectron2.config import get_cfg
+from detectron2.data.detection_utils import read_image
+from detectron2.utils.logger import setup_logger
+
+from predictor import VisualizationDemo
+
+# constants
+WINDOW_NAME = "COCO detections"
+
+
+def setup_cfg(args):
+    # load config from file and command-line arguments
+    cfg = get_cfg()
+    cfg.merge_from_file(args.config_file)
+    cfg.merge_from_list(args.opts)
+    # Set score_threshold for builtin models
+    cfg.MODEL.RETINANET.SCORE_THRESH_TEST = args.confidence_threshold
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = args.confidence_threshold
+    cfg.MODEL.PANOPTIC_FPN.COMBINE.INSTANCES_CONFIDENCE_THRESH = args.confidence_threshold
+    cfg.freeze()
+    return cfg
+
+
+def get_parser():
+    parser = argparse.ArgumentParser(description="Detectron2 Demo")
+    parser.add_argument(
+        "--config-file",
+        default="configs/quick_schedules/e2e_mask_rcnn_R_50_FPN_inference_acc_test.yaml",
+        metavar="FILE",
+        help="path to config file",
+    )
+    
+    
+    parser.add_argument(
+        "--confidence-threshold",
+        type=float,
+        default=0.5,
+        help="Minimum score for instance predictions to be shown",
+    )
+    parser.add_argument(
+        "--opts",
+        help="Modify model config options using the command-line",
+        default=[],
+        nargs=argparse.REMAINDER,
+    )
+    return parser
+
+
+if __name__ == "__main__":
+    mp.set_start_method("spawn", force=True)
+    args = get_parser().parse_args()
+    logger = setup_logger()
+    logger.info("Arguments: " + str(args))
+
+    cfg = setup_cfg(args)
+
+
+    demo = VisualizationDemo(cfg)
+    f = open("/mnt/datasets/vlog/list.txt", "r")
+    for x in f:
+        print(x)
+        
+        video = cv2.VideoCapture("/mnt/datasets/vlog/"+x[:-1])
+        fourcc = cv2.VideoWriter_fourcc(*'XVID')
+        output_file="/mnt/datasets/vlog/"+x[:-8]+"with_object_detection"+".avi"
+        out = cv2.VideoWriter(output_file,fourcc, 20.0, (256,256))
+        while(video.isOpened()):
+            ret,frame = video.read()
+            if ret==True:
+                predictions, visualized_output = demo.run_on_image(frame)
+                out.write(visualized_output.get_image()[:, :, ::-1])
+                if cv2.waitKey(1) & 0xFF == ord('q'):
+                    break
+            else:
+                break 
+        video.release()
+        out.release()
+        cv2.destroyAllWindows()   
+
+