COCO

Software / App

A dataset commonly used in computer vision, mentioned in the context of creating a new benchmark for SAM 3.

Mentioned in 4 videos

Videos Mentioning COCO

Segment Anything 2: Memory + Vision = Object Permanence — with Nikhila Ravi and Joseph Nelson

Segment Anything 2: Memory + Vision = Object Permanence — with Nikhila Ravi and Joseph Nelson

Latent Space

A dataset traditionally used for object detection, containing common objects in context. It's mentioned as a benchmark that researchers like Pete Dollar, head of Nikhila's group, are now encouraging to move beyond for more generalized capabilities.

MIT 6.S093: Introduction to Human-Centered Artificial Intelligence (AI)

MIT 6.S093: Introduction to Human-Centered Artificial Intelligence (AI)

Lex Fridman

A dataset for object detection, segmentation, and captioning, featuring rich annotations for localization.

MIT 6.S094: Computer Vision

MIT 6.S094: Computer Vision

Lex Fridman

A large-scale dataset used in computer vision research, mentioned alongside ImageNet and Places.

SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow)

SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow)

Latent Space

A dataset commonly used in computer vision, mentioned in the context of creating a new benchmark for SAM 3.