auto grading for 3d modeling assignments in moocs
play

Auto-grading for 3D Modeling Assignments in MOOCs Swapneel Mehta - PowerPoint PPT Presentation

Aug 02, 2023 •183 likes •670 views

Auto-grading for 3D Modeling Assignments in MOOCs Swapneel Mehta Nitin Ayer Chirag Raman Sameer Sahasrabudhe Motivation 2 SKANI101XA Basic 3D Animation Using Blender Introductory course on 3D animation Motivation User Workflows Proposed

  1. Auto-grading for 3D Modeling Assignments in MOOCs Swapneel Mehta Nitin Ayer Chirag Raman Sameer Sahasrabudhe

  2. Motivation 2

  3. SKANI101XA Basic 3D Animation Using Blender Introductory course on 3D animation Motivation User Workflows Proposed System Summary 3

  4. SKANI101XA Basic 3D Animation Using Blender Introductory course on 3D animation The course has been offered five times with an average of ~ 4000 enrolled students! Motivation User Workflows Proposed System Summary 4

  5. SKANI101XA Basic 3D Animation Using Blender Introductory course on 3D animation The course has been offered five times with an average of ~ 4000 enrolled students! Assignments include generating simple 3D models Motivation User Workflows Proposed System Summary 5

  6. Modeling Assignment A drill activity early in the course to demonstrate basic concepts of face selection and extrusion The intention is for the students to exactly follow the steps of the drill Motivation User Workflows Proposed System Summary 6

  7. Modeling Assignment Motivation User Workflows Proposed System Summary 7

  8. Modeling Assignment Motivation User Workflows Proposed System Summary 8

  9. Modeling Assignment Motivation User Workflows Proposed System Summary 9

  10. Modeling Assignment Motivation User Workflows Proposed System Summary 10

  11. General Errors Incomplete Model! Motivation User Workflows Proposed System Summary 11

  12. General Errors Incomplete Primitive! - Cube instead of Torus Motivation User Workflows Proposed System Summary 12

  13. Motivation Around 25% of the students submit the first assignment Submissions are .blend files, not images Motivation User Workflows Proposed System Summary 13

  14. Motivation Around 25% of the students submit the first assignment Submissions are .blend files, not images Grading is a resource intensive task! Motivation User Workflows Proposed System Summary 14

  15. Typical User Workflows 15

  16. IITBombayX Motivation User Workflows Proposed System Summary 16

  17. IITBombayX Students Motivation User Workflows Proposed System Summary 17

  18. IITBombayX Students Instructors Motivation User Workflows Proposed System Summary 18

  19. IITBombayX Content Management System Students Instructors Motivation User Workflows Proposed System Summary 19

  20. IITBombayX Content Management System Students Coursework Instructors Motivation User Workflows Proposed System Summary 20

  21. IITBombayX Learning Content Management Management System System Students Instructors Motivation User Workflows Proposed System Summary 21

  22. IITBombayX Learning Content Assignment Management Management System System Students Instructors Motivation User Workflows Proposed System Summary 22

  23. IITBombayX Submissions (.blend) Learning Content Management Management System System Students Instructors Motivation User Workflows Proposed System Summary 23

  24. IITBombayX Submissions (.blend) Learning Content Management Management System System Students Instructors Motivation User Workflows Proposed System Summary 24

  25. IITBombayX IITBombayX Submissions (.blend) Learning Content Management Management System System Students Submissions Instructors Motivation User Workflows Proposed System Summary 25

  26. IITBombayX Learning Content Management Management System System Students Assessments Instructors Motivation User Workflows Proposed System Summary 26

  27. IITBombayX Learning Content Management Management System System Students Assessments Instructors Motivation User Workflows Proposed System Summary 27

  28. IITBombayX Learning Content Assessments Management Management System System Students Assessments Instructors Motivation User Workflows Proposed System Summary 28

  29. Proposed System Auto-grading for 3D Modeling Assignments in MOOCs 29

  30. Auto-grader IITBombayX Learning Content Management Management Students System System Instructors Motivation User Workflows Proposed System Summary 30

  31. Auto-grader IITBombayX Rubric Learning Content Management Management Students System System Instructors Motivation User Workflows Proposed System Summary 31

  32. Auto-grader IITBombayX Rubric Submission Learning Content Management Management Students System System Instructors Motivation User Workflows Proposed System Summary 32

  33. Auto-grader IITBombayX Submission Rubric Submission Learning Content Management Management Students System System Instructors Motivation User Workflows Proposed System Summary 33

  34. Auto-grader IITBombayX Submission Rubric Learning Content Management Management Students System System Comparer Instructors Motivation User Workflows Proposed System Summary 34

  35. Auto-grader IITBombayX Submission Rubric Learning Content Management Management Students System System Comparer Assessor Instructors Motivation User Workflows Proposed System Summary 35

  36. Auto-grader IITBombayX Submission Rubric Learning Content Management Management Students System System Comparer Assessor Instructors Motivation User Workflows Proposed System Summary 36

  37. Auto-grader IITBombayX Submission Rubric Learning Content Assessments Management Management Students System System Comparer Assessor Instructors Motivation User Workflows Proposed System Summary 37

  38. Comparer Attributes extracted from the .blend files 01 | Object Placement (Location, Rotation) 02 | Polygon Count 03 | Number of Objects 04 | Additional Free Parameter Motivation User Workflows Proposed System Summary 38

  39. Comparer Implemented as a Python script using the Blender 3D API Motivation User Workflows Proposed System Summary 39

  40. Assessor - Grading Policy Generates assessments and feedback from the Comparer output using instructor specified grading policy ATTRIBUTE 1 0 Object Placement At origin, identity rotation Otherwise Polygon Count 576 +/- 100 Otherwise Number of Objects 1 Otherwise Additional Parameter (Type) Torus Otherwise Motivation User Workflows Proposed System Summary 40

  41. Assessor Grades are assigned as an ordinal score in the range [0, 5] Motivation User Workflows Proposed System Summary 41

  42. Assessor Grades are assigned as an ordinal score in the range [0, 5] FUTURE EXTENSIONS: Perform direct mesh-based evaluation ● Provide customized feedback ● Motivation User Workflows Proposed System Summary 42

  43. Assessor Motivation User Workflows Proposed System Summary 43

  44. Summary 44

  45. Introduced a stand-alone auto-grading module that incorporates an instructor defined rubric for the automatic assessment of submitted 3D modeling assignments Motivation User Workflows Proposed System Summary 45

  46. Future directions include integration with LTI tools, incorporating an intelligent sub-module for direct mesh-based evaluation, and providing customized feedback Motivation User Workflows Proposed System Summary 46

  47. Thank you! Questions? 47

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Auto-grading for 3D Modeling Assignments in MOOCs Swapneel Mehta Sameer Sahasrabudhe Dept. of

Auto-grading for 3D Modeling Assignments in MOOCs Swapneel Mehta Sameer Sahasrabudhe Dept. of

Auto-grading for 3D Modeling Assignments in MOOCs Swapneel Mehta Sameer Sahasrabudhe Dept. of Computer Engineering Dept. of Computer Science and Engineering D. J. Sanghvi College of Engg. Indian Institute of Technology Bombay, Powai Mumbai,

385 views • 3 slides
What is Computing? Grading Tues/Thurs 4-5:30 pm in Park 349 7 Assignments 42% 6

What is Computing? Grading Tues/Thurs 4-5:30 pm in Park 349 7 Assignments 42% 6

CMSC B110: Introduction to Computing Spring 2012 Section 1 Mark F. Russo, Ph.D. Email: mfrusso@brynmawr.edu Email: russomf@gmail.com Lectures What is Computing? Grading Tues/Thurs 4-5:30 pm in Park 349 7 Assignments 42% 6

299 views • 9 slides
GRADING. YOU LOVE IT. AGENDA! Grade What You Value! Grading Essays & Time

GRADING. YOU LOVE IT. AGENDA! Grade What You Value! Grading Essays & Time

JAM Sesh 2014 GRADING. YOU LOVE IT. AGENDA! Grade What You Value! Grading Essays & Time Management! Plotting Out Assignments! What to Do When Kids Are Slipping! GRADE WHAT YOU VALUE Correctness/Completeness

138 views • 9 slides
Assignments Please fill the dropboxes Lights Still catching up on grading.

Assignments Please fill the dropboxes Lights Still catching up on grading.

Assignments Please fill the dropboxes Lights Still catching up on grading. Questions. Final exam effects Final exam effect Deliverables: Presentation: Research (Grads only) Final exam period Shader code

457 views • 11 slides
STUDENT-LED ASSESSMENT: RUBRIC DEVELOPMENT AND PEER GRADING IN WRITING ASSIGNMENTS Presented by

STUDENT-LED ASSESSMENT: RUBRIC DEVELOPMENT AND PEER GRADING IN WRITING ASSIGNMENTS Presented by

STUDENT-LED ASSESSMENT: RUBRIC DEVELOPMENT AND PEER GRADING IN WRITING ASSIGNMENTS Presented by Brice Particelli, PhD English Department, New York City 2017 Faculty Institute, Pace University LIST What do you expect from a good Faculty

609 views • 18 slides
Assignments Please fill the dropboxes Volumetric Shaders Still catching up on grading.

Assignments Please fill the dropboxes Volumetric Shaders Still catching up on grading.

Assignments Please fill the dropboxes Volumetric Shaders Still catching up on grading. Questions. Final exam effects Final exam effect Deliverables: Presentation: Research (Grads only) Final exam period Shader

493 views • 10 slides
CHAPTER-1 1 Expert Systems Grading: Midterm Exam % 25 Project /Assignments/Quizzes

CHAPTER-1 1 Expert Systems Grading: Midterm Exam % 25 Project /Assignments/Quizzes

CHAPTER-1 1 Expert Systems Grading: Midterm Exam % 25 Project /Assignments/Quizzes % 50 Final Exam % 25 Textbook: Joseph Giarratano and Gary Riley. Expert Systems: Principles and Programming. 3 rd edition, PWS Publishing,

548 views • 29 slides
Lets Talk About MOOCs (After All, Everybody Else Is ) Dan Grossman University of

Lets Talk About MOOCs (After All, Everybody Else Is ) Dan Grossman University of

Lets Talk About MOOCs (After All, Everybody Else Is ) Dan Grossman University of Washington Department of Computer Science & Engineering October 5, 2012 My plan My roles related to MOOCs Personal take on why I will teach

313 views • 10 slides
Logistics Paper summaries on Procedural Modeling Procedural Modeling Any takers?

Logistics Paper summaries on Procedural Modeling Procedural Modeling Any takers?

Logistics Paper summaries on Procedural Modeling Procedural Modeling Any takers? Assignments Assignments Write-ups for all 3 projects now on Web Ray Tracing Round off error New Due Dates Ambient or no ambient

459 views • 11 slides
MOOCs Betters Education and Teaching- t he Case of Shanghai Jiao Tong University and its CnMOOC Dr

MOOCs Betters Education and Teaching- t he Case of Shanghai Jiao Tong University and its CnMOOC Dr

MOOCs Betters Education and Teaching- t he Case of Shanghai Jiao Tong University and its CnMOOC Dr Zhibin Jiang Dean of MOOCs Institute and Chair Professor and Head of IEM& Department of SJTU Outline MOOCs development in China 1 Massive and

550 views • 52 slides
Grading for Equity Guidelines for Grading in an Online Environment Key Questions Around Grading

Grading for Equity Guidelines for Grading in an Online Environment Key Questions Around Grading

Grading for Equity Guidelines for Grading in an Online Environment Key Questions Around Grading How do grading practices need to differ in a distance learning environment? What do we need to keep in mind when grading for equity? Belief

831 views • 36 slides
Behavioral Modeling Verilog Synthesis Examples Using continuous assignments ISE can build

Behavioral Modeling Verilog Synthesis Examples Using continuous assignments ISE can build

Behavioral Modeling Verilog Synthesis Examples Using continuous assignments ISE can build you a nice adder Easier than specifying your own CS/EE 3710 Fall 2010 Mostly from CMOS VLSI Design by Weste and Harris Bitwise Operators

317 views • 7 slides
Behavioral Modeling Using continuous assignments ISE can build you a nice adder Easier

Behavioral Modeling Using continuous assignments ISE can build you a nice adder Easier

Verilog Synthesis Examples CS/EE 3710 Fall 2010 Mostly from CMOS VLSI Design by Weste and Harris Behavioral Modeling Using continuous assignments ISE can build you a nice adder Easier than specifying your own 1 Bitwise Operators

471 views • 19 slides
Language Modeling CSE354 - Spring 2020 Task Language Modeling Probabilistic Modeling

Language Modeling CSE354 - Spring 2020 Task Language Modeling Probabilistic Modeling

Language Modeling CSE354 - Spring 2020 Task Language Modeling Probabilistic Modeling h o w ? (i.e. auto-complete) Probability Theory Logistic Regression Sequence Modeling Language Modeling -- assigning a

761 views • 53 slides
MOOCs @ Maryland Ben Bederson Associate Provost of Learning Initiatives Exec. Dir. of Teaching

MOOCs @ Maryland Ben Bederson Associate Provost of Learning Initiatives Exec. Dir. of Teaching

Massive Open Online Courses MOOCs @ Maryland Ben Bederson Associate Provost of Learning Initiatives Exec. Dir. of Teaching & Learning Transformation Center 1 03-Bederson MOOCs - HCIL SOH - May 2014 - June 2, 2014 2 03-Bederson MOOCs -

168 views • 14 slides
Debugging Auto-Generated Code with Source Specification in Exploratory Modeling Tomohiro Oda

Debugging Auto-Generated Code with Source Specification in Exploratory Modeling Tomohiro Oda

Overture Workshop 15 : New Capabilities and Applications for Model-based Systems Engineering Debugging Auto-Generated Code with Source Specification in Exploratory Modeling Tomohiro Oda Keijiro Araki Peter Gorm Larsen Agenda Exploratory

143 views • 13 slides
Structural analysis of expected and unexpected clauses in sentences using gaze-tracking studies

Structural analysis of expected and unexpected clauses in sentences using gaze-tracking studies

Structural analysis of expected and unexpected clauses in sentences using gaze-tracking studies Chirag Gupta IIT Kanpur October 20, 2012 Introduction Consider the following sentences The ball was kicked by Bhutia into the goal. The

345 views • 23 slides
The most famous math textbook in history Chirag Kalelkar National Chemical Laboratory Pune At

The most famous math textbook in history Chirag Kalelkar National Chemical Laboratory Pune At

The most famous math textbook in history Chirag Kalelkar National Chemical Laboratory Pune At the age of 12, I experienced a wonder of a totally different nature: in a book dealing with Euclidean geometry, which came into my hands at the

544 views • 19 slides
ASIC Clouds: Specializing the Datacenter Ikuo Magaki, Moein Khazraee, Luis Vega Gutierrez, and

ASIC Clouds: Specializing the Datacenter Ikuo Magaki, Moein Khazraee, Luis Vega Gutierrez, and

ASIC Clouds: Specializing the Datacenter Ikuo Magaki, Moein Khazraee, Luis Vega Gutierrez, and Michael Bedford Taylor UC San Diego and Toshiba Presented By: Vandit Agarwal Motivation GPU and FPGA based clouds already successful Even ASIC

620 views • 27 slides
SYSC3601 Microprocessor Systems Unit 5: Memory Structures and Interfacing SYSC3601 1

SYSC3601 Microprocessor Systems Unit 5: Memory Structures and Interfacing SYSC3601 1

SYSC3601 Microprocessor Systems Unit 5: Memory Structures and Interfacing SYSC3601 1 Microprocessor Systems Topics/Reading 1. Memory Types 2. Interfacing 8-bit memory/IO (8088) 3. Interfacing 16-bit memory/IO (8086) 4. Interfacing

823 views • 39 slides
IDC Update on How Big Data Is Redefining High Performance Computing Earl Joseph

IDC Update on How Big Data Is Redefining High Performance Computing Earl Joseph

IDC Update on How Big Data Is Redefining High Performance Computing Earl Joseph ejoseph@idc.com Steve Conway sconway@idc.com Chirag Dekate cdekate@idc.com Bob Sorensen bsorensen@idc.com IDC Has Over 1,000 Analysts In 62 Countries

964 views • 59 slides
Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Devices

Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Devices

Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Devices Albert Gural 1 , Boris Murmann 1 1 Stanford University The 36 th International Conference on Machine Learning Long Beach, California June 11, 2019

405 views • 15 slides
Anne)Bracy: Career)Path Undergrad)@)Stanford Grad)School)@)UPenn (computer)architecture)

Anne)Bracy: Career)Path Undergrad)@)Stanford Grad)School)@)UPenn (computer)architecture)

Anne)Bracy: Career)Path Undergrad)@)Stanford Grad)School)@)UPenn (computer)architecture) Intel)Labs Anne$Bracy Lecturer)@)Washington)University)in)St.)Louis Computer)Science Cornell Cornell)University Just)moved)here

491 views • 14 slides
Multiple Instance Learning for Fast, Stable and Early RNN Predictions Don Dennis , Microsoft

Multiple Instance Learning for Fast, Stable and Early RNN Predictions Don Dennis , Microsoft

The Edge of Machine Learning Multiple Instance Learning for Fast, Stable and Early RNN Predictions Don Dennis , Microsoft Research India, Joint work with Chirag P., Harsha and Prateek Accepted to NIPS 18 1 Algorithms for the IDE - EdgeML

977 views • 70 slides

More recommend