CS 6674

Last Updated

  • Schedule of Classes - January 5, 2026 3:59PM EST

CS 6674
Multimodal Computer Vision

Course information provided by the 2025-2026 Catalog.

Multimodal representations are reshaping computer vision, driving advances in both understanding and generation across a wide range of perceptual tasks. This research-oriented course explores computer vision techniques that integrate images with additional modalities such as language and 3D geometry for addressing challenges in both analysis and synthesis tasks. Possible topics include visual grounding, multimodal alignment, and text-guided generation and editing over multiple 2D and 3D representations.


Enrollment Priority Enrollment limited to: Cornell Tech PhD Students. Recommended prerequisites: CS 3780/CS 5780 or equivalent, CS 5670 or equivalent.

Last 1 Terms Offered (None)

View Enrollment Information

Syllabi: none

  •   Regular Academic Session. 

  • 3 Credits Graded

  • 18477 CS 6674   LEC 001

  •  

  • Instruction Mode: Distance Learning-Synchronous

Syllabi: none

  •   Regular Academic Session. 

  • 3 Credits Graded

  • 18466 CS 6674   LEC 030

  •  

  • Instruction Mode: In Person

    Enrollment limited to Cornell Tech PhD Students only.