Apple is presenting new analysis on the annual convention on IEEE/CVF Convention on Laptop Imaginative and prescient and Sample Recognition (CVPR), which takes place in particular person in Nashville, Tennessee from June 11 to June 15. We’re proud to sponsor the convention, which brings collectively the scientific and industrial analysis communities in pc imaginative and prescient and sample recognition. Beneath is an outline of Apple’s participation at CVPR 2025.
Bounce to a piece:
Schedule
Cease by the Apple sales space within the Music Metropolis Middle, sales space #1217, throughout exhibition hours. All occasions listed in CDT (Nashville time):
- Friday, June 13: 10:00am – 6:30pm
- Saturday, June 14: 10:00am – 6:30pm
- Sunday, June 15: 10:00am – 3:00pm
Wednesday, June 11
- WORKSHOP
- Laptop Imaginative and prescient for Metaverse Workshop (CV4Metaverse) 2025
- 8:10am – 12:20pm, Room 107 A
-
- POSTER
- “A Stereo Picture High quality Predictor for AR/VR”
- Netanel Tamir (Weizmann Institute of Science), Shir Amir, Ranel Itzhaky, Noam Atia (Tel Aviv College), Shobhita Sundaram (Massachusetts Institute of Know-how), Stephanie Fu (Massachusetts Institute of Know-how), Miriam Farber, Ron Sokolovsky, Richard Zhang (Impartial researcher), Tali Dekel (Weizmann Institute of Science), Phillip Isola (Massachusetts Institute of Know-how)
- WORKSHOP
- Nice-Grained Visible Categorization (FGVC12) 2025
- 9:00am – 5:15pm, Room 104 E
-
- POSTER
- “Rethinking Semi-Supervised Area Adaptation for Semantic Segmentation with Semi-Supervised Studying within the Basis Mannequin Period”
- Joshua Kurien (College of Waterloo), Bavesh Balaji (College of Waterloo), Henry Lai, Pablo Guerrero Vela, C Thomas, Alex Wong, Sirisha Rambhatla
Thursday, June 12
- WORKSHOP
- Ladies in Laptop Imaginative and prescient (WiCV)
- 8:30am – 1:00pm (Workshop), Room 105 B
- 6:00pm – 8:00pm (Mentorship Dinner), Room 202 C
- Fazilet Gokbudak, Jess Knowles, and Michael Kirchhof can be representing Apple on the WiCV Mentorship Dinner
Friday, June 13
- HIGHLIGHT POSTER
- Multimodal Autoregressive Pre-Coaching of Giant Imaginative and prescient Encoders
- 4:00pm – 6:00pm, #407, Poster Session 2, Exhibit Corridor D
- Enrico Fini, Mustafa Shukor (Sorbonne College), Xiujun Li, Philipp Dufter, Michal Klein, David Haldimann, Sai Aitharaju, Louis Béthune, Zhe Gan, Victor Turrisi, Alexander Toshev, Marcin Eichner, Yinfei Yang, Moin Nabi, Josh Susskind, Alaaeldin El-Nouby
Saturday, June 14
- ORAL PRESENTATION
- From Multimodal LLMs to Generalist Embodied Brokers: Strategies and Classes
- 9:00am – 10:15am, Presentation #5, Oral Session 3, Davidson Ballroom
- Andrew Szot (Georgia Institute of Know-how), Bogdan Mazoure, Omar Attia, Aleksei Timofeev, Harsh Agrawal, Devon Hjelm, Zhe Gan, Zsolt Kira (Georgia Institute of Know-how), Alexander Toshev
- POSTER
- From Multimodal LLMs to Generalist Embodied Brokers: Strategies and Classes
- 10:30am – 12:30pm, #329, Poster Session 3, Exhibit Corridor D
- Andrew Szot (Georgia Institute of Know-how), Bogdan Mazoure, Omar Attia, Aleksei Timofeev, Harsh Agrawal, Devon Hjelm, Zhe Gan, Zsolt Kira (Georgia Institute of Know-how), Alexander Toshev
- HIGHLIGHT POSTER
- Matrix3D: Giant Photogrammetry Mannequin All-in-One
- 10:30am – 12:30pm, #57, Poster Session 3, Exhibit Corridor D
- Yuanxun Lu (Nanjing College), Jingyang Zhang, Tian Fang, Danny Nahmias, Yanghai Tsin, Lengthy Quan (Hong Kong College of Science and Know-how), Xun Cao (Nanjing College), Yao Yao (Nanjing College), Shiwei Li
- POSTER
- FastVLM: Environment friendly Imaginative and prescient Encoding for Imaginative and prescient Language Fashions
- 5:00pm – 7:00pm, #378, Poster Session 4, Exhibit Corridor D
- Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pour Ansari
Sunday, June 15
Sales space Programming & Demos
Go to Apple’s sales space at Music Metropolis Middle, Sales space #1217, throughout exhibition hours.
Featured Analysis Periods
Technical Demos
- DEMO
- FastVLM
- FastVLM is a household of mobile-friendly imaginative and prescient language fashions.These fashions use a mixture of CNN and Transformer architectures for imaginative and prescient encoding designed particularly for processing high-resolution photographs. Collectively, they ship the perfect stability between accuracy and velocity.
- Friday, June 13: 10:00am – 12:30pm, 2:30pm – 4:30pm
- Saturday, June 14: 10:00am – 12:30pm, 2:30pm – 4:30pm
- Sunday, June 15: 10:00am – 12:30pm
Accepted Papers
- FastVLM: Environment friendly Imaginative and prescient Encoding for Imaginative and prescient Language Fashions
- Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pour Ansari
- Matrix3D: Giant Photogrammetry Mannequin All-in-One
- Yuanxun Lu (Nanjing College), Jingyang Zhang, Tian Fang, Danny Nahmias, Yanghai Tsin, Lengthy Quan (Hong Kong College of Science and Know-how), Xun Cao (Nanjing College), Yao Yao (Nanjing College), Shiwei Li
- Multimodal Autoregressive Pre-training of Giant Imaginative and prescient Encoders
- Enrico Fini, Mustafa Shukor (Sorbonne College), Xiujun Li, Philipp Dufter, Michal Klein, David Haldimann, Sai Aitharaju, Louis Béthune, Zhe Gan, Victor Turrisi, Alexander Toshev, Marcin Eichner, Yinfei Yang, Moin Nabi, Josh Susskind, Alaaeldin El-Nouby
Acknowledgements
Jack Langerman is Workshop Co-Organizer for the Workshop on City Scene Modeling: The place Imaginative and prescient Meets Photogrammetry and Graphics at CVPR.
Jeff Bigham is Workshop Co-Organizer for the VizWiz Grand Problem Workshop at CVPR.
Qi Shan is Session Chair for CVPR.
Alex Colburn, Fartash Faghri, Hadi Pour Ansari, Mingze Xu, and Oncel Tuzel are Space Chairs for CVPR.
Amin Karimi Monsefi, Andrew Szot, Guandao Yang, Harsh Agrawal, Helisa Dhamo, Huangjie Zheng, Jack Langerman, Jiatao Gu, Liangchen Music, Michael Kirchhof, Marcin Eichner, Noam Elata, Pavan Kumar Anasosalu Vasu, Peter Fu, Raviteja Vemulapalli, Shaobo Fang, Rick Chang, Xiaoming Zhao, and Xudong Liu are Reviewers for CVPR.
