Загрузка видео...

Не удалось загрузить видео

На главную

NEVER LOOK BACK! Introducing LEDGER: persistent 3D object memory from egocentric videos. Remember where things were, when they moved, and what they held -> then answer questions without looking back at the video!

12,620 просмотров • 17 дней назад •via X (Twitter)

Комментарии: 8

Фото профиля Homanga Bharadhwaj
Homanga Bharadhwaj17 дней назад

This was a fun project led by @Shra_1_C along with William Paul, and Johns Hopkins colleagues @suchisaria and Rama Chellappa Thread with details from @Shra_1_C below

Фото профиля Dominik
Dominik17 дней назад

object permanence for agents is so underrated. does ledger track things that leave the frame for hours, like keys that got moved by someone else while the wearer was out?

Фото профиля Sani Ai Tech
Sani Ai Tech17 дней назад

Persistent 3D memory could be a huge step for egocentric AI systems

Фото профиля Vera Ai | Tools & Updates
Vera Ai | Tools & Updates16 дней назад

Persistent 3D memory could be a major leap for embodied AI reasoning

Фото профиля LM10/7
LM10/716 дней назад

Actually solid, also real-time implementation will make this🤌🏼

Фото профиля Zara Tech & Tools
Zara Tech & Tools16 дней назад

Smart approach to remembering object history

Фото профиля Vantix AI Agency
Vantix AI Agency16 дней назад

Persistent 3D object memory from egocentric video is wild answering where things were without rewatching is huge

Фото профиля Veyra | AI & Tech
Veyra | AI & Tech16 дней назад

Egocentric video memory that actually persists

Похожие видео