Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
220
datasets available to search
ShareScore release 0.9.0
Dataset results
220 results for “Landmark”
Fig. 1, a in Determination Of Sexual Dimorphism And Morphological Variation Of Pool Barb, Puntius Sophore (Cypriniformes, Cyprinidae), Using Landmark Based Geometric Morphometric Analysis
Fig. 1, a — male individual in breeding season; b — digitized image of P. sophore with the 14 landmarks (red points) used for the geometric morphometric analysis: c — scatter plot of 14 landmarks configurations after Procrustes Superimposition.
Fig. 2 in Determination Of Sexual Dimorphism And Morphological Variation Of Pool Barb, Puntius Sophore (Cypriniformes, Cyprinidae), Using Landmark Based Geometric Morphometric Analysis
Fig. 2. Distribution of non-breeding season population and the breeding season (male and female) population along first and second canonical variate axes (female in red, male in blue and non-breeding season population in green).
Dataset: Landmark Bancorp, Inc. (LARK) Stock Performance
This dataset provides historical stock market performance data for specific companies. It enables users to analyze and understand the past trends and fluctuations in stock prices over time. This information can be utilized for various purposes such as investment analysis, financial research, and market trend forecasting.
Map. Species diversity of Diplopoda within the Sikhote-Alin State Nature Biosphere Reserve. The numbers of the natural landmarks (1–18) are explained in the "Material and Methods section" Карта. ВиΑовое разнообразие Αвупарноногих многоножек в Сихотэ-АΛинском заповеΑнике. Номера урочищ (1–18) поясняются в разΑеΛе «МатериаΛ и метоΑы» in Review of the millipedes of the Sikhote-Alin State Nature Biosphere Reserve (Far East of Russia), with detection of the morphological variability of Diplomaragna terricolor (Attems, 1899) (Diplopoda)
Map. Species diversity of Diplopoda within the Sikhote-Alin State Nature Biosphere Reserve. The numbers of the natural landmarks (1–18) are explained in the "Material and Methods section" Карта. ВиΑовое разнообразие Αвупарноногих многоножек в Сихотэ-АΛинском заповеΑнике. Номера урочищ (1–18) поясняются в разΑеΛе «МатериаΛ и метоΑы»
FIGURE 13. Superimposed landmark diagrams visualizing shape changes between M1 in Identifying tooth position of isolated teeth of sparassodonts (Mammalia: Metatheria) using geometric morphometrics
FIGURE 13. Superimposed landmark diagrams visualizing shape changes between M1 (large gray circles) and M3 (small black circles) of selected non-borhyaenid sparassodonts: (A) Allqokirus australis (MNHC 8267), (B) Patene coluapiensis (AMNH 28448), (C) Procladosictis anomala (MACN-A 10327), (D) Hondadelphys fieldsi (UCMP 37960), (E) Sipalocyon gracilis (AMNH 9254), (F) Lycopsis longirostrus (UCMP 38061), (G) Prothylacynus patagonicus (MACN-A 707), (H) Thylacosmilus atrox (MMP 1443).
Fig. 1 Landmarks used for the kinematic analyses. 1 upper jaw tip, 2 lower jaw tip, 3 in Flexibility is everything: prey capture throughout the seasonal habitat switches in the smooth newt Lissotriton vulgaris
Fig. 1 Landmarks used for the kinematic analyses. 1 upper jaw tip, 2 lower jaw tip, 3 hyoid (throat), 4 jaw joint, 5 nape, 6 dorsal trunk reference, 7 tongue tip (only digitized when visible)
Fig. 2 Landmark templates for representative a lateral and b in Revision of the genus complex Gibbula: an integrative approach to delineating the Eastern Mediterranean genera Gibbula Risso, 1826, Steromphala Gray, 1847, and Phorcus Risso, 1826 using DNA-barcoding and geometric morphometrics (Vetigastropoda, Trochoidea)
Fig. 2 Landmark templates for representative a lateral and b ventral standardised views. Filled circles show fixed landmarks. Empty circles show semilandmarks, processed as sliding landmarks
RAVDESS Facial Landmark Tracking
<p><strong>Contact Information</strong></p> <p>If you would like further information about the RAVDESS Facial Landmark Tracking data set, or if you experience any issues downloading files, please contact us at <a href="mailto:ravdess@gmail.com?subject=RAVDESS%20feedback%20from%20Zenodo">ravdess@gmail.com</a>. </p> <p><strong>Tracking Examples</strong></p> <p>Watch a sample of the <a href="https://youtu.be/cxMK2J0P7J0">facial tracking results</a>.</p> <p><strong>Description</strong></p> <p>The <a href="https://affectivedatascience.com/datasets.html#landmark-tracking">RAVDESS Facial Landmark Tracking dataset</a> set contains tracked facial landmark movements from the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) [<a href="https://zenodo.org/record/1188976">RAVDESS Zenodo page</a>]. Motion tracking of actors' faces was produced by OpenFace 2.1.0 (Baltrusaitis, T., Zadeh, A., Lim, Y. C., & Morency, L. P., 2018). Tracked information includes: facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.</p> <p>The Facial Landmark Tracking dataset was created in the <a href="https://affectivedatascience.com">Affective Data Science Lab</a>.</p> <p>This data set contains tracking for all 2452 RAVDESS trials. All tracking movement data are contained in "FacialTracking_Actors_01-24.zip", which contains 2452 .CSV files. Each actor has 104 tracked trials (60 speech, 44 song). Note, there are no song files for Actor 18.</p> <p>Total Tracked Files = (24 Actors x 60 Speech trials) + (23 Actors x 44 Song trials) = 2452 files.</p> <p>Tracking results for each trial are provided as individual comma separated value files (CSV format). File naming convention of tracked files is identical to that of the RAVDESS. For example, tracked file "01-01-01-01-01-01-01.csv" corresponds to RAVDESS audio-video file "01-01-01-01-01-01-01.mp4". For a complete description of the RAVDESS file naming convention and experimental manipulations, please see the <a href="https://zenodo.org/record/1188976">RAVDESS Zenodo page</a>. </p> <p>Tracking overlay videos for all trials are also provided (720p Xvid, .avi), one zip file per Actor. As the RAVDESS does not contain "ground truth" facial landmark locations, the overlay videos provide a visual 'sanity check' for researchers to confirm the general accuracy of the tracking results. The file naming convention of tracking overlay videos also matches that of the RAVDESS. For example, tracking video "01-01-01-01-01-01-01.avi" corresponds to RAVDESS audio-video file "01-01-01-01-01-01-01.mp4".</p> <p><strong>Tracking File Output Format</strong></p> <p>This data set retained OpenFace's data output format, <a href="https://github.com/TadasBaltrusaitis/OpenFace/wiki/Output-Format">described here in detail</a>. The resolution of all input videos was 1280x720. When tracking output units are in pixels, their range of values is (0,0) (top left corner) to (1280,720) (bottom right corner). </p> <p><em>Columns 1-3 = Timing and Detection Confidence</em></p> <ul> <li>1. Frame - The number of the frame (source videos 30 fps), range = 1 to n</li> <li>2. Timestamp - Time of frame, range = 0 to m</li> <li>3. Confidence - Tracker confidence level in current landmark detection estimate, range = 0 to 1</li> </ul> <p><em>Columns 4-291 = Eye Gaze Detection</em></p> <ul> <li>4-6. gaze_0_x, gaze_0_y, gaze_0_z - Eye gaze direction vector in world coordinates for eye 0 (normalized), eye 0 is the leftmost eye in the image (think of it as a ray going from the left eye in the image in the direction of the eye gaze).</li> <li>7-9. gaze_1_x, gaze_1_y, gaze_1_z - Eye gaze direction vector in world coordinates for eye 1 (normalized), eye 1 is the rightmost eye in the image (think of it as a ray going from the right eye in the image in the direction of the eye gaze).</li> <li>10-11. gaze_angle_x, gaze_angle_y - Eye gaze direction in radians in world coordinates, averaged for both eyes. If a person is looking left-right this will results in the change of gaze_angle_x (from positive to negative) and, if a person is looking up-down this will result in change of gaze_angle_y (from negative to positive), if a person is looking straight ahead both of the angles will be close to 0 (within measurement error).</li> <li>12-123. eye_lmk_x_0, ..., eye_lmk_x55, eye_lmk_y_0,..., eye_lmk_y_55 - Location of 2D eye region landmarks in pixels. A figure describing the landmark index <a href="https://raw.githubusercontent.com/wiki/TadasBaltrusaitis/OpenFace/images/eye_lmk_markup.png">can be found here</a>.</li> <li>124-291. eye_lmk_X_0, ..., eye_lmk_X55, eye_lmk_Y_0,..., eye_lmk_Y_55,..., eye_lmk_Z_0,..., eye_lmk_Z_55 - Location of 3D eye region landmarks in millimeters. A figure describing the landmark index <a href="https://raw.githubusercontent.com/wiki/TadasBaltrusaitis/OpenFace/images/eye_lmk_markup.png">can be found here</a>.</li> </ul> <p><em>Columns 292-297 = Head pose</em></p> <ul> <li>292-294. pose_Tx, pose_Ty, pose_Tz - Location of the head with respect to camera in millimeters (positive Z is away from the camera).</li> <li>295-297. pose_Rx, pose_Ry, pose_Rz - Rotation of the head in radians around X,Y,Z axes with the convention R = Rx * Ry * Rz, left-handed positive sign. This can be seen as pitch (Rx), yaw (Ry), and roll (Rz). The rotation is in world coordinates with the camera being located at the origin.</li> </ul> <p><em>Columns 298-433 = Facial Landmarks locations in 2D</em></p> <ul> <li>298-433. x_0, ..., x_67, y_0,...y_67 - Location of 2D landmarks in pixels. A figure describing the landmark index <a href="https://raw.githubusercontent.com/TadasBaltrusaitis/OpenFace/master/imgs/landmark_scheme_68.png">can be found here</a>.</li> </ul> <p><em>Columns 434-637 = Facial Landmarks locations in 3D</em></p> <ul> <li>434-637. X_0, ..., X_67, Y_0,..., Y_67, Z_0,..., Z_67 - Location of 3D landmarks in millimetres. A figure describing the landmark index <a href="https://raw.githubusercontent.com/TadasBaltrusaitis/OpenFace/master/imgs/landmark_scheme_68.png">can be found here</a>. For these values to be accurate, OpenFace needs to have good estimates for fx,fy,cx,cy.</li> </ul> <p><em>Columns 638-677 = Rigid and non-rigid shape parameters</em></p> <p>Parameters of a point distribution model (PDM) that describe the rigid face shape (location, scale and rotation) and non-rigid face shape (deformation due to expression and identity). For more details, please refer to chapter 4.2 of my Tadas Baltrusaitis's PhD thesis [<a href="https://www.repository.cam.ac.uk/handle/1810/245253">download link</a>].</p> <ul> <li>638-643. p_scale, p_rx, p_ry, p_rz, p_tx, p_ty - Scale, rotation, and translation terms of the PDM.</li> <li>644-677. p_0, ..., p_33 - Non-rigid shape parameters.</li> </ul> <p><em>Columns 687-712 = Facial Action Units</em></p> <p>Facial Action Units (AUs) are a way to describe human facial movements (Ekman, Friesen, and Hager, 2002) [<a href="https://en.wikipedia.org/wiki/Facial_Action_Coding_System">wiki link</a>]. More information on OpenFace's implementation of AUs <a href="https://github.com/TadasBaltrusaitis/OpenFace/wiki/Action-Units">can be found here</a>.</p> <ul> <li>678-694. AU01_r, AU02_r, AU04_r, AU05_r, AU06_r, AU07_r, AU09_r, AU10_r, AU12_r, AU14_r, AU15_r, AU17_r, AU20_r, AU23_r, AU25_r, AU26_r, AU45_r - Intensity of AU movement, range from 0 (no muscle contraction) to 5 (maximal muscle contraction).</li> <li>695-712. AU01_c, AU02_c, AU04_c, AU05_c, AU06_c, AU07_c, AU09_c, AU10_c, AU12_c, AU14_c, AU15_c, AU17_c, AU20_c, AU23_c, AU25_c, AU26_c, AU28_c, AU45_c - Presence or absence of 18 AUs, range 0 (absent, not detected) to 1 (present, detected).</li> </ul> <p>Note, OpenFace's columns 2 and 5 (face_id and success, respectively) were not included in this data set. These values were redundant as a single face was detected in all frames, in all 2452 trials.</p> <p><strong>Tracking Overlay Videos</strong></p> <p>Tracking overlay videos visualize most aspects of the tracking output described above.</p> <ul> <li>Frame - Column 1, Top left corner of video</li> <li>Eye Gaze - Columns 4-11. Indicated by green ray emanating from left and right eyes.</li> <li>Eye region landmarks 2D - Columns 12-123. Red landmarks around left and right eyes, and black circles surrounding left and right irises.</li> <li>Head pose - Columns 292-297. Blue bounding box surrounding the actor's head.</li> <li>Facial landmarks 2D - Columns 298-433. Red landmarks on the participant's left and right eyebrows, nose, lips, and jaw.</li> <li>Facial Action Unit Intensity - Columns 687-694. All 17 AUs are listed on the left side of the video in black text. Intensity level (0-5) of each AU is indicated by the numeric value and blue bar.</li> <li>Facial Action Unit Presence - Columns 695-712. All 18 AUs are listed on the right side of the video in black & green text. Absence of an AU (0) is in black text with the numeric value 0.0. Presence of an AU (1) is in green text with the numeric value 1.0.</li> </ul> <p><strong>Camera Parameters and 3D Calibration Procedure</strong></p> <p>This data set contains accurate estimates of actors' 3D head poses. To produce these, camera parameters at the time of recording were required (distance from camera to actor, and camera field of view). These values were used with OpenCV's camera calibration procedure, <a href="https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_calib3d/py_calibration/py_calibration.html">described here</a>, to produce estimates of the camera's focal length and optical center at the time of actor recordings. The four values produced by the calibration procedure (fx,fy,cx,cy) were input to OpenFace as command line arguments during facial tracking, <a href="https://github.com/TadasBaltrusaitis/OpenFace/wiki/Command-line-arguments">described here</a>, to produce accurate estimates of 3D head pose.</p> <p><em>Camera Parameters</em></p> <ul> <li>Distance between camera and actor = 1.4 meters</li> <li>Camera field of view = 0.5 meters</li> <li>Focal length in x (fx) = 6385.9</li> <li>Focal length in y (fy) = 6339.6</li> <li>Optical center in x (cx) = 824.241</li> <li>Optical center in y (cy) = 1033.6</li> </ul> <p>The use of OpenCV's calibration procedure was required as the video camera used in the RAVDESS recordings did not report focal length values. Unlike SLR cameras, most video cameras do not provide this information to the user due to their dynamic focus feature. For all RAVDESS recordings, camera distance, field of view, and focal point (manual fixed camera focus) were kept constant.</p> <p><strong>License information</strong></p> <p>The RAVDESS Facial Landmark Tracking data set is released under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License, <a href="https://creativecommons.org/licenses/by-nc-sa/4.0/">CC BY-NA-SC 4.0</a>.</p> <p><strong>How to cite the RAVDESS Facial Tracking data set</strong></p> <p><em>Academic citation </em><br>If you use the RAVDESS Facial Tracking data set in an academic publication, please cite both references: </p> <ol> <li>Swanson, R., Livingstone, SR., & Russo, FA. (2019). RAVDESS Facial Landmark Tracking (Version 1.0.0) [Data set]. Zenodo. http://doi.org/10.5281/zenodo.3255102</li> <li>Livingstone SR, Russo FA (2018) The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE 13(5): e0196391. <a href="https://doi.org/10.1371/journal.pone.0196391">https://doi.org/10.1371/journal.pone.0196391</a>.</li> </ol> <p><em>All other attributions </em><br>If you use the RAVDESS in a form other than an academic publication, such as in a blog post, school project, or non-commercial product, please use the following attribution: "<a href="https://zenodo.org/record/3255102">RAVDESS Facial Landmark Tracking</a>" by Swanson, Livingstone, & Russo is licensed under <a href="https://creativecommons.org/licenses/by-nc-sa/4.0/">CC BY-NA-SC 4.0</a>.</p> <p><strong>Related Data sets</strong></p> <ul> <li>The Ryerson Audio-Visual Database of Emotional Speech and Song [<a href="https://zenodo.org/record/1188976">Zenodo project page</a>].</li> </ul>
Fig. 2. Landmarks and semilandmarks designated using tpsDIG for 2D in Ontogenetic changes in the craniomandibular skeleton of the abelisaurid dinosaur Majungasaurus crenatissimus from the Late Cretaceous of Madagascar
Fig. 2. Landmarks and semilandmarks designated using tpsDIG for 2D data (A) and landmark for 3D data (B). Landmark configurations aligned using generalized procrustes analysis, removing the effects of size, orientation, and position (C, D). Ontogenetic shape change visualized by generating deformation grids for 2D data (E) and warped meshes for 3D data (F).
Fig. 1. Landmark configurations maped onto a hypothetical generalized henricosborniid. A in Early steps in the radiation of notoungulate mammals in southern South America: A new henricosborniid from the Eocene of Patagonia
Fig. 1. Landmark configurations maped onto a hypothetical generalized henricosborniid. A. Upper molar: 1, metastyle; 2, metacone; 3, paracone; 4, parastyle; 5, protocone; 6, hypocone; 7, distolingual end of crochet; 8, mesiolabial end of crochet. B. Lower molar: 1, labial end of paralophid; 2, labial end of metalophid; 3, lingual end of metalophid; 4, mesial end of cristid obliqua; 5, hypoconulid; 6, entoconid/lingual end of entolophid.
Fig. 3. Eight landmarks and 89 in Late Cretaceous record of large soft-bodied coleoids based on lower jaw remains from Hokkaido, Japan
Fig. 3. Eight landmarks and 89 semi-landmarks collected on a coleoid lower jaw (A, B). 1, the rostral tip; 2, the base of the rostrum; 3, the posterior end of the wing; 4, the posterior intersection of the outer and inner lamellae; 5, the posterior end of the inner lamella; 6, the anteroventral end of the crest; 7, the anterior intersection of the outer and inner lamellae; 8, the anteroventral end of the hood. B. A square grid showing shape differences between two individuals as deformation from B to B drawn by use of a thin-plate spline.
Facial Expression and Landmark Tracking (FELT) dataset
<p><strong>Contact Information</strong></p> <p>If you would like further information about the Facial expression and landmark tracking data set, or if you experience any issues downloading files, please contact us at <a href="mailto:ravdess@gmail.com?subject=RAVDESS%20feedback%20from%20Zenodo">ravdess@gmail.com</a>. </p> <p><strong>Facial Expression examples</strong></p> <p>Watch a sample of the <a href="https://youtu.be/OA5gZ6iycPc">facial expression tracking results</a>.</p> <p><strong>Commercial Licenses</strong></p> <p>Commercial licenses for this dataset can be purchased. For more information, please contact us at <a href="mailto:ravdess@gmail.com?subject=RAVDESS%20Commercial%20License">ravdess@gmail.com</a>.</p> <p><strong>Description</strong></p> <p>The <a href="https://affectivedatascience.com/datasets.html#felt">Facial Expression and Landmark Tracking (FELT) dataset</a> dataset contains tracked facial expression movements and animated videos from the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) [<a href="../record/1188976">RAVDESS Zenodo page</a>]. Tracking data and videos were produced by Py-Feat 0.6.2 (2024-03-29 release) (Cheong, J.H., Jolly, E., Xie, T. <em>et al.</em> Py-Feat: Python Facial Expression Analysis Toolbox. <em>Affec Sci</em> <strong>4</strong>, 781–796 (2023). https://doi.org/10.1007/s42761-023-00191-4) and custom code (<a href="https://github.com/harveyliao/Py-feat-RAVDESS">github repo</a>). Tracked information includes: facial emotion classification estimates, facial landmark detection (68 points), head pose estimation (yaw, pitch, roll, x, y), and facial Action Unit (AU) recognition. Videos include: landmark overlay videos, AU activation animations, and landmark plot animations.</p> <p>The FELT dataset was created at the <a href="https://affectivedatascience.com">Affective Data Science Lab</a>.</p> <p>This dataset contains tracking data and videos for all 2452 RAVDESS trials. Raw and smoothed tracking data are provided. All tracking movement data are contained in the following archives: raw_motion_speech.zip, smoothed_motion_speech.zip, raw_motion_song.zip, and smoothed_motion_song.zip. Each actor has 104 tracked trials (60 speech, 44 song). Note, there are no song files for Actor 18.</p> <p>Total Tracked Files = (24 Actors x 60 Speech trials) + (23 Actors x 44 Song trials) = 2452 CSV files.</p> <p>Tracking results for each trial are provided as individual comma separated value files (CSV format). File naming convention of raw and smoothed tracked files is identical to that of the RAVDESS. For example, smoothed tracked file "01-01-01-01-01-01-01.csv" corresponds to RAVDESS audio-video file "01-01-01-01-01-01-01.mp4". For a complete description of the RAVDESS file naming convention and experimental manipulations, please see the <a href="../record/1188976">RAVDESS Zenodo page</a>. </p> <p>Landmark overlays, AU activation, and landmark plot videos for all trials are also provided (720p h264, .mp4). Landmark overlays present tracked landmarks and head pose overlaid on the original RAVDESS actor video. As the RAVDESS does not contain "ground truth" facial landmark locations, the overlay videos provide a visual 'sanity check' for researchers to confirm the general accuracy of the tracking results. Landmark plot animations present landmarks only, anchored to the top left corner of the head bounding box with translational head motion removed. AU activation animations visualize intensity of AU activations (0-1 normalized) as a heatmap over time. The file naming convention of all videos also matches that of the RAVDESS. For example, "Landmark_Overlay/01-01-01-01-01-01-01.mp4", "Landmark_Plot/01-01-01-01-01-01-01.mp4", "ActionUnit_Animation/01-01-01-01-01-01-01.mp4", all correspond to RAVDESS audio-video file "01-01-01-01-01-01-01.mp4".</p> <p><strong>Smoothing procedure<br></strong></p> <p>Raw tracking data were first low-pass filtered with a 5th order butterworth filter (cutoff_freq = 6, sampling_freq = 29.97, order = 5) to remove high-frequency noise. Data were then smoothed with a Savitzky-Golay filter (window_length = 11, poly_order = 5). Scipy.signal (v 1.13.1) was used for both procedures.</p> <p><strong>Landmark Tracking models</strong></p> <p>Six separate machine learning models were used by Py-Feat to perform various aspects of tracking and classification. Video outputs generated by different combinations of ML models were visually compared, with final model choice determined by voting of first and second authors. Models were specified in the call to <code>Detector</code> class (<a href="https://py-feat.org/basic_tutorials/02_detector_imgs.html?highlight=facescore">described here</a>). Exact function call as follows:</p> <p><code> Detector(face_model='img2pose',</code><br><code> landmark_model='mobilenet',</code><br><code> au_model='xgb',</code><br><code> emotion_model='resmasknet',</code><br><code> facepose_model='img2pose-c',</code><br><code> identity_model='facenet',</code><br><code> device='cuda',</code><br><code> n_jobs=1,</code><br><code> verbose=False,</code><br><code> )</code></p> <p>Default Py_feat parameters to each model were used in most cases. Non-defaults were specified in the call to <code>detect_video</code> function (<a href="https://py-feat.org/pages/api.html?highlight=detect_video">described here</a>). Exact function call as follows:<br><br><code> (video_path,</code><br><code> skip_frames=None,</code><br><code> output_size=(720, 1280),</code><br><code> batch_size=5,</code><br><code> num_workers=0,</code><br><code> pin_memory=False,</code><br><code> face_detection_threshold=0.83,</code><br><code> face_identity_threshold=0.8</code><br><code> )</code></p> <p><strong>Tracking File Output Format</strong></p> <p>This data set retained Py-Feat's data output format. The resolution of all input videos was 1280x720. Tracking output units are in pixels, their range of values is (0,0) (top left corner) to (1280,720) (bottom right corner). </p> <p><em>Column 1 = Timing information</em></p> <ul> <li>1. frame - The number of the frame (source videos 29.97 fps), range = 1 to n</li> </ul> <p><em>Columns 2-5 = Head bounding box<br></em></p> <ul> <li>2-3. FaceRectX, FaceRectY - X and Y coordinates of top-left corner of head bounding box (pixels)</li> <li>4-5. FaceRectWidth, FaceRectHeightF - Width and Height of head bounding box (pixels)</li> </ul> <p><em>Column 6 = Face detection confidence<br></em></p> <ul> <li>FaceScore - Confidence level that a human face was deteceted, range = 0 to 1</li> </ul> <p><em>Columns 7-142 = Facial landmark locations in 2D<br></em></p> <ul> <li>7-142. x_0, ..., x_67, y_0,...y_67 - Location of 2D landmarks in pixels. A figure describing the landmark index <a href="https://raw.githubusercontent.com/TadasBaltrusaitis/OpenFace/master/imgs/landmark_scheme_68.png">can be found here</a>.</li> </ul> <p><em>Columns 143-145 = Head pose</em></p> <ul> <li>143-145. Pitch, Roll, Yaw - Rotation of the head in degrees (<a href="https://py-feat.org/basic_tutorials/02_detector_imgs.html?highlight=facerect#:~:text=single_face_prediction.poses%20%23%20(in%20degrees)">described here</a>). The rotation is in world coordinates with the camera being located at the origin.</li> </ul> <p><em>Columns 146-165 = </em><em>Facial Action Units</em></p> <p>Facial Action Units (AUs) are a way to describe human facial movements (Ekman, Friesen, and Hager, 2002) [<a href="https://en.wikipedia.org/wiki/Facial_Action_Coding_System">wiki link</a>]. More information on Py-Feat's implementation of AUs <a href="https://py-feat.org/pages/au_reference.html">can be found here</a>.</p> <ul> <li>145-150, 152-153, 155-158, 160-165. AU01, AU02, AU04, AU05, AU06, AU09, AU10, AU12, AU14, AU15, AU17, AU23, AU24, AU25, AU26, AU28, AU43 - Intensity of AU movement, range from 0 (no muscle contraction) to 1 (maximal muscle contraction).</li> <li>151, 154, 159. AU07, AU11, AU20 - Presence or absence of AUs, range 0 (absent, not detected) to 1 (present, detected).</li> </ul> <p><em>Columns 166-172 = Emotion classification confidence<br></em></p> <ul> <li>162-172. anger, disgust, fear, happiness, sadness, surprise, neutral - Confidence of classified emotion category, range 0 (0%) to 1 (100%) confidence.</li> </ul> <p><em>Columns 173-685 = Face identity score<br></em></p> <p>Identity of faces contained in the video were classified using the FaceNet model (<a href="https://arxiv.org/pdf/1503.03832">described here</a>). This procedure generates at 512 dimension Euclidean embedding space.</p> <ul> <li>173. Identity - Predicated individual identifyed in the RAVDESS video. Note, value is always Person_0, as each video only contains a single actor at all times (categorical).</li> <li>174-685. Identity_1, ..., Identity_512 - Face embedding vector used by FaceNet to perform facial identity matching.</li> </ul> <p><em>Column 686 = Input video<br></em></p> <ul> <li>686. frame - The number of the frame (source videos 29.97 fps), range = 1 to n</li> </ul> <p><em>Columns 687-688 = Timing information<br></em></p> <ul> <li>687. frame.1 - The number of the frame (source videos 29.97 fps), duplicated column, range = 1 to n</li> <li>688. approx_time - Approximate time of current frame (0.0 to x.x, in seconds)</li> </ul> <p><strong>Tracking videos<br></strong></p> <p>Landmark Overlay and Landmark Plot videos were produced with <code>plot_detections</code> function call (<a href="https://py-feat.org/pages/api.html?highlight=plot_detections#feat.data.Fex.plot_detections">described here</a>). This function generated invidual images for each frame, which were then compiled into a video using the imageio library (<a href="https://pypi.org/project/imageio/">described here</a>).</p> <p>AU Activation videos were produced with plot_face function call (<a href="https://py-feat.org/pages/api.html?highlight=plot_face#feat.plotting.plot_face">described here</a>). This function also generated invidual images for each frame, which were then compiled into a video using the imageio library. Some frames could not be correctly generated by Py-Feat, producing only the AU heatmap but failing to plot/locate facial landmarks. These frames were dropped prior to compositing the output video. Drop rate was approximately 10% of all frames, in each video. Dropped frames were distributed evenly across the video timeline (i.e. no apparent clustering).</p> <p><strong>License information</strong></p> <p>The RAVDESS Facial expression and landmark tracking data set is released under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License, <a href="https://creativecommons.org/licenses/by-nc-sa/4.0/">CC BY-NA-SC 4.0</a>.</p> <p><strong>How to cite the RAVDESS Facial Tracking data set</strong></p> <p><em>Academic citation </em><br>If you use the RAVDESS Facial Tracking data set in an academic publication, please cite both references: </p> <ol> <li>Liao, Z., Livingstone, SR., & Russo, FA. (2024). RAVDESS Facial expression and landmark tracking (Version 1.0.0) [Data set]. Zenodo. http://doi.org/10.5281/zenodo.13243600</li> <li>Livingstone SR, Russo FA (2018). The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE 13(5): e0196391. <a href="https://doi.org/10.1371/journal.pone.0196391">https://doi.org/10.1371/journal.pone.0196391</a>.</li> </ol> <p><em>All other attributions </em><br>If you use the RAVDESS Facial expression and landmark tracking dataset in a form other than an academic publication, such as in a blog post, data science project or competition, school project, or non-commercial product, please use the following attribution: "<a href="../records/13243600">RAVDESS Facial expression and landmark tracking</a>" by Liao, Livingstone, & Russo is licensed under <a href="https://creativecommons.org/licenses/by-nc-sa/4.0/">CC BY-NA-SC 4.0</a>.</p> <p><strong>Related Data sets</strong></p> <ul> <li>The Ryerson Audio-Visual Database of Emotional Speech and Song [<a href="../record/1188976">Zenodo project page</a>].</li> </ul> <p> </p>
Landmark dataset of fore wings of Darwin wasps (Ichneumonidae)
<p>This tps file includes the forewing landmark data of Darwin wasps (Ichneumonidae). The fore wing shape is defined with 21 fixed landmarks and additionally 1 curve consisting of 8 semi landmarks which represent the vein 2m-cu (landmarks equally spaced).</p> <p>Included are 669 taxa, representing 41 extant subfamilies. The landmark data of 333 extant taxa were published before in Viertler et al. (2022), and are here included together with many more taxa. The newly added data might still be errouneous. The landmarks were mainly placed on illustrations of Townes (see references), but some were added from photos of the respective species.</p>
Tsetse fly wing landmark data for morphometrics (Vol 20, 21)
<p>Single-wing images were captured from 14,354 pairs of field-collected tsetse wings of species <em>Glossina</em> <em>pallidipes</em> and <em>G</em>. <em>m</em>. <em>morsitans</em> and analysed together with relevant biological data. To answer research questions regarding these flies, we need to locate 11 anatomical landmark coordinates on each wing. The manual location of landmarks is time-consuming, prone to error, and simply infeasible given the number of images. Automatic landmark detection has been proposed to locate these landmark coordinates. We developed a two-tier method using deep learning architectures to classify images and make accurate landmark predictions. The first tier used a classification convolutional neural network to remove most wings that were missing landmarks. The second tier provided landmark coordinates for the remaining wings. For the second tier, compared direct coordinate regression using a convolutional neural network and segmentation using a fully convolutional network. For the resulting landmark predictions, we evaluate shape bias using Procrustes analysis. We employ a data-centric approach paying particular attention to consistent labelling and data augmentations in training data to improve model performance. The classification model used for the first tier achieved perfect classification on the test set. For an image size of 1024×1280, data augmentation reduced the mean pixel distance error from 8.3 (95% CI [4.4,10.3]) to 5.34 (95% CI [3,7]) for the regression model. For the segmentation model, data augmentation did not alter the mean pixel distance error of 3.43 (95% CI [1.9,4.4]). Segmentation had a higher computational complexity and some large outliers. Both models showed minimal shape bias. We chose to deploy the regression model on complete unannotated data since the regression model had a lower computational cost and more stable predictions than the segmentation model. The resulting landmark dataset was provided for future morphometric analysis.</p>
Ecological signal in the size and shape of marine amniote teeth – 3D models and landmarks
<p class="MsoNormal"><span>Amniotes have been a major component of marine trophic chains from the beginning of the Triassic to present day, with hundreds of species. However, inferences of their (palaeo)ecology have mostly been qualitative, making it difficult to track how dietary niches have changed through time and across clades. Here, we tackle this issue by applying a novel geometric morphometric protocol to 3D models of tooth crowns across a wide range of raptorial marine amniotes. Our </span><span>results highlight the phenomenon of dental simplification and widespread convergence in marine amniotes, implying strong functional constraints which limit the range of tooth crown morphologies. </span><span>Importantly, we quantitatively demonstrate that tooth </span><span>crown form (shape plus size) is strongly associated with diet, whereas crown surface complexity is not. The maximal range of tooth shapes in both mammals and reptiles is seen in medium-sized taxa; large crowns are simple and restricted to a fraction of the morphospace. </span><span>We recognise four principle raptorial guilds within toothed marine amniotes (durophages, generalists, meat cutters, and flesh piercers). Moreover, even though all these feeding guilds have been convergently colonised over the last 200 million years, a series of dental morphologies are unique to the Mesozoic period, probably reflecting a distinct ecosystem structure.</span></p>
Armed to the teeth: Supplementary material, R code, Rdata, mesh, landmarks
<p>The structure, composition, and shape of teeth have been related to dietary specialization in many vertebrate species, but comparative studies on snakes' teeth are lacking. Yet, snakes have diverse dietary habits that may impact the shape of their teeth. We hypothesize that prey properties, such as hardness and shape, as well as feeding behavior, such as aquatic or arboreal predation, or holding vigorous prey, impose constraints on the evolution of tooth shape in snakes. We compared the morphology of the dentary teeth of 63 species that cover the phylogenetic and dietary diversity of snakes, using 3D geometric morphometrics and linear measurements. Our results show that prey hardness, foraging substrate, and the main foraging mechanical challenge are important drivers of tooth shape, size, and curvature. Overall, long, slender, curved teeth with a thin layer of hard tissue are observed in species that need to maintain a grip on their prey. Short, stout, less curved teeth are associated with species that undergo high or repeated loads. Our study demonstrates the diversity of tooth morphology in snakes and the need to investigate its underlying functional implications to better understand the evolution of teeth in vertebrates.</p>
17 Landmarks from modern human skulls
<p>Coordinates of 17 landmarks of modern human skulls. They have not been subjected to Procrustes superimposition. See paper from Bucchi and Fonseca for details: Shape variation among skull regions using geometric morphometrics.</p> <p>Open in R: readRDS(file = "data.rds")</p> <p>The skulls are held at the Subactual Collection of Santiago (Facultad de Ciencias Sociales, Universidad de Chile)</p> <p>Landmark configuration:</p> <table align="left"> <tbody> <tr> <td> <p>Number</p> </td> <td> <p>Landmark</p> </td> <td> <p>Location</p> </td> </tr> <tr> <td> <p>1</p> </td> <td> <p>Nasion</p> </td> <td> <p>The point of the intersection between the frontonasal suture and the midsagittal plane</p> </td> </tr> <tr> <td> <p>2, 8</p> </td> <td> <p>Fontomalar (paired: right and left)</p> </td> <td> <p>Most anterior point of the zygomaticofrontal suture</p> </td> </tr> <tr> <td> <p>3, 9</p> </td> <td> <p>Superior zigotemporale (paired)</p> </td> <td> <p>Most superior point in the temporozygomatic suture</p> </td> </tr> <tr> <td> <p>4, 10</p> </td> <td> <p>Porion (paired)</p> </td> <td> <p>Lateral most part of the superior margin of the external auditory meatus</p> </td> </tr> <tr> <td> <p>5, 11</p> </td> <td> <p>Mastoidale (paired)</p> </td> <td> <p>point at the lowest point of the mastoid process</p> </td> </tr> <tr> <td> <p>6, 12</p> </td> <td> <p>Zygomaxillare (paired)</p> </td> <td> <p>Most inferior point in the zygomaticomaxillary suture</p> </td> </tr> <tr> <td> <p>7, 13</p> </td> <td> <p>Ectomalare (paired)</p> </td> <td> <p>The most posterior point on the alveolar bone</p> </td> </tr> <tr> <td> <p>14, 16</p> </td> <td> <p>Pterion (paired)</p> </td> <td> <p> Intersection of the frontal, sphenoid, parietal and the squamous part of temporal bone</p> </td> </tr> <tr> <td> <p>15, 17</p> </td> <td> <p>Asterion (paired)</p> </td> <td> <p>Point where the temporal, parietal and occipital bones meet</p> </td> </tr> </tbody> </table> <p> </p>
Figure 3 in Absence of visual cues motivates desert ants to build their own landmarks
Figure 3. Ants build their own landmark by increasing their nest hill's height (A) Experimental design. Nest hills were first measured (height) and removed from 16 salt pan nests of which only eight were afterward provided with two artificial landmarks each. 3 days later, we re-measured rebuilt nest hills. (B) Photograph of the artificial landmarks added to a nest. (C) Percentage of the original nest rebuilt at nests with landmarks present or absent (unpaired t test, *p <0.05, bars indicate median ± SD).
Figure 2 in Absence of visual cues motivates desert ants to build their own landmarks
Figure 2. Absence of a nest hill impairs the navigation of salt pan ants (A–F) Trajectories of zero-vector ants of a salt pan nest (A–C) or shore nest (D–F) with nest hill present (left) or absent (right) after 5, 7.5, and 10 m displacement (colored circumferences indicate each displacement distance). Highlighted in bold is a trajectory exemplar of an ant for each displacement distance. (G–I) Straightness scores (i.e., run length divided by beeline) of homing ants of both nest types for the different displacement distances (Kruskal-Wallis test with Dunn's multiple comparisons test for selected pairs, **p <0.01; ***p <0.001, bars indicate median ± SD). (J–L) Success rates of homing ants of both nest types for the different displacement distances (Fisher's exact test, *p <0.05). Ants that during nest search left the tracking grid (radius, 20 m) around the nest entrance were classified as ''unsuccessful'' and are represented as crosses at the edges of the arenas.
Figure 1 in Absence of visual cues motivates desert ants to build their own landmarks
Figure 1. Accuracy of long homing runs and survey of nests in a salt pan (A) GPS tracks of long foraging runs (Geo Tracker, Google Earth) (see also Figure S1). Each black dot represents a different nest. Black lines, successful homing runs; red lines, unsuccessful homing runs that resulted in the ant's death. The track that leads to colony E is displaced to fit closer to the other paths for visualization purposes. (B) Photographs of a typical salt pan nest (left) and a typical shore nest (right, photo credit: Cornelia Buehlmann). (C) Map of the salt pan with dominant environmental features (i.e., vegetation and terrain elevations) and classifications of two nest types. Nests located at least 60 m away from any shoreline are classified as salt pan nests (blue) and nests less than 40 m away from any shoreline are classified as shore nests (green). Nests situated between 40 and 60 m from any shoreline are not included in the analysis. (D) Height of nest hills at salt pan nests and shore nests (unpaired t test, n = 33; ****p <0.0001; bars indicate median and SD). See also Table S1.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.