Schedule (CAP6412 – Spring 2022)
| Date | Paper | Presenter | Discussion |
|---|---|---|---|
| 1/10/22 | Artificial Intelligence Revolution [PDF of Presentation] [Video of Presentation] | Dr. Shah | |
| 1/12/22 | Advances in Computer Vision Employing Deep Learning [PDF of Presentation] [Video of Presentation] | Dr. Shah | |
| 1/17/22022 | Martin Luther King Jr. Day No Class | ||
| 1/19/22 | Transformer [PDF of Presentation] [Video of Presentation] | Dr. Shah | |
| 1/24/22 | VIT, DeIT, SWIN [PDF of Presentation] [Video of Presentation] | Dr. Shah | |
| 1/26/22 | DETr, TimeS, ViViT [PDF of Presentation] [Video of Presentation] | Dr. Shah | |
| 1/31/22 | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [ViT (ICLR)] [PDF of Presentation] [Video of Presentation] | A: Joseph Rivera, Michael Fielder, Kishore Kumar Alajangi, James Dwyer | B: Mateus Urbanski, Ryan Glaspey, Crystal Gagne, Nathaniel Houlihan |
| 2/2/22 | Training data-efficient image transformers & distillation through attention [DeiT (ICML)] [PDF of Presentation] [Video of Presentation] | C: Moazam Soomro, Fatemah Najafali, Alec Kerrigan, Connor Maley | D: Anshuman Gaharwar, Parth Kulkarni, Abhishek Maruturi, Sarath Mannam, Akashdeep Chakraborty |
| 2/7/22 | Swin Transformer: Hierarchical Vision Transformer using Shifted Windows [Swin Transformer (ICCV)] [PDF of Presentation] [Video of Presentation] | E: Avirup Ghosh, Rishabh Patel, Shenyang Liu, Shiyi Gong | D: Anshuman Gaharwar, Parth Kulkarni, Abhishek Maruturi, Sarath Mannam, Akashdeep Chakraborty |
| 2/9/22 | ViViT: A Video Vision Transformer [ViViT (ICCV)] [PDF of Presentation] [Video of Presentation] | D: Anshuman Gaharwar, Parth Kulkarni, Abhishek Maruturi, Sarath Mannam, Akashdeep Chakraborty | F: George Lu, Sarah Wilson, Adam Kutchak, Fernando Trevino Ramirez |
| 2/14/22 | Is Space-Time Attention All You Need for Video Understanding? [Time transformer (ICML)] [PDF of Presentation] [Video of Presentation] | B: Mateus Urbanski, Ryan Glaspey, Crystal Gagne, Nathaniel Houlihan | A: Joseph Rivera, Michael Fielder, Kishore Kumar Alajangi, James Dwyer |
| 2/16/22 | Project Presentations | ||
| 2/21/22 | Video Swin Transformer [Video Swin Transformer] [PDF of Presentation] [Video of Presentation] | B: Mateus Urbanski, Ryan Glaspey, Crystal Gagne, Nathaniel Houlihan | E: Avirup Ghosh, Rishabh Patel, Shenyang Liu, Shiyi Gong |
| 2/23/22 | End-to-End Object Detection with Transformers [DETR (ECCV)] [PDF of Presentation] [Video of Presentation] | F: George Lu, Sarah Wilson, Adam Kutchak, Fernando Trevino Ramirez | G: Brandon Clark, Dunquan Zheng, Alejandro Zamora, Joshua Gracie |
| 2/28/22 | Deformable DETR: Deformable Transformers for End-to-End Object Detection [Deformable DETR (ICLR) [PDF of Presentation] [Video of Presentation] | H: Jacob Pfaffenbichler, Sharon Barak, Tristan de Blegiers, Jacob O'Quinn | F: George Lu, Sarah Wilson, Adam Kutchak, Fernando Trevino Ramirez |
| 3/2/22 | Learning Transferable Visual Models From Natural Language Supervision [CLIP (ICML)] [PDF of Presentation] [Video of Presentation] | C: Moazam Soomro, Fatemah Najafali, Alec Kerrigan, Connor Maley | B: Mateus Urbanski, Ryan Glaspey, Crystal Gagne, Nathaniel Houlihan |
| 3/7/22 | Spring Break | ||
| 3/9/22 | Spring Break | ||
| 3/14/22 | Perceiver: General Perception with Iterative Attention [Perceiver (ICML)] [PDF of Presentation] [Video of Presentation] | G: Brandon Clark, Dunquan Zheng, Alejandro Zamora, Joshua Gracie | A: Joseph Rivera, Michael Fielder, Kishore Kumar Alajangi, James Dwyer |
| 3/16/22 | Project Presentations [Video of Presentation] [Video of 2nd Presentation] | ||
| 3/21/22 | No Class | ||
| 3/23/22 | Taming Transformers for High-Resolution Image Synthesis [VQGAN (CVPR)] [PDF of Presentation] [Video of Presentation] | I: Sanjay Shanbhag, Momal Ijaz, Mehdi Yazdani-Jahromi, Kasun Tharuka Dewage Dane Bouchie | H: Jacob Pfaffenbichler, Sharon Barak, Tristan de Blegiers, Jacob O'Quinn |
| 3/28/22 | Zero-Shot Text-to-Image Generation [DALL.E (ICML)] [PDF of Presentation] [Video of Presentation] | F: George Lu, Sarah Wilson, Adam Kutchak, Fernando Trevino Ramirez | E: Avirup Ghosh, Rishabh Patel, Shenyang Liu, Shiyi Gong |
| 3/30/22 | Intriguing Properties of Vision Transformers [Intriguing Properties of Vision Transformers (NEURIPS)] [PDF of Presentation] [Video of Presentation] | A: Joseph Rivera, Michael Fielder, Kishore Kumar Alajangi, James Dwyer | I: Sanjay Shanbhag, Momal Ijaz, Mehdi Yazdani-Jahromi, Kasun Tharuka Dewage, Dane Bouchie |
| 4/4/22 | A ConvNet for the 2020s [ConvNeXt] [PDF of Presentation] [Video of Presentation] | I: Sanjay Shanbhag, Momal Ijaz, Mehdi Yazdani-Jahromi, Kasun Tharuka Dewage, Dane Bouchie | H: Jacob Pfaffenbichler, Sharon Barak, Tristan de Blegiers, Jacob O'Quinn |
| 4/6/22 | Multiview Transformers for Video Recognition [Multiview Transformers] [PDF of Presentation] [Video of Presentation] | D: Anshuman Gaharwar, Parth Kulkarni, Abhishek Maruturi, Sarath Mannam, Akashdeep Chakraborty | C: Moazam Soomro, Fatemah Najafali, Alec Kerrigan, Connor Maley |
| 4/11/22 | Rethinking and Improving Relative Position Encoding for Vision Transformer [Relative Position Encoding (ICCV)] [PDF of Presentation] [Video of Presentation] | E: Avirup Ghosh, Rishabh Patel, Shenyang Liu, Shiyi Gong | C: Moazam Soomro, Fatemah Najafali, Alec Kerrigan, Connor Maley |
| 4/13/22 | Project Presentations [Video of Presentation] | ||
| 4/18/22 | Emerging Properties in Self-Supervised Vision Transformers [DINO (ICCV)] [PDF of Presentation] [Video of Presentation] | H: Jacob Pfaffenbichler, Sharon Barak, Tristan de Blegiers, Jacob O'Quinn | G: Brandon Clark, Dunquan Zheng, Alejandro Zamora, Joshua Gracie |
| 4/20/22 | Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers [SETR (CVPR)] [PDF of Presentation] [Video of Presentation] | G: Brandon Clark, Dunquan Zheng, Alejandro Zamora, Joshua Gracie | I: Sanjay Shanbhag, Momal Ijaz, Mehdi Yazdani-Jahromi, Kasun Tharuka Dewage, Dane Bouchie |
| 4/25/22 | No presentation | ||
| 4/27/22 | Final Project Presentation: 1:00-4:00 [Video of Presentation] |