Miao

31 posts

Miao banner
Miao

Miao

@aptx4869ml

Phd student in Robotics @GeorgiaTech, interested in computer vision and robotics

Atlanta, GA Katılım Ekim 2016
37 Takip Edilen44 Takipçiler
Miao
Miao@aptx4869ml·
(7/n)Lego leverages egocentric vLLM to generate enriched action description, and feed the enriched description together with the vLLM embeddings to SDMl to generate an action frame vividly depicts how an action should be conducted based on the user’s visual context.
English
0
0
0
65
Miao
Miao@aptx4869ml·
(6/n)thanks to the wonderful job from Bolin during his internship at Meta GenAI, we bring Lego to the community.
English
1
0
0
71
Miao
Miao@aptx4869ml·
(5/n)The rest of the story is obvious. By marrying egocentric vision and generative models including vLLM and SDM, there is an exciting opportunity to directly generate a pixel-level representation to address the howto problem.
English
1
0
0
66
Miao
Miao@aptx4869ml·
(2/n)Baby step, we started with action recognition. Yet, action recognition will serve as a trigger of all the magical things we envision the egocentric AI system will offer. For the howto problem, the model needs to output fine grained representation than simply answering whatis
English
1
0
0
61
Miao
Miao@aptx4869ml·
(4/n)After joining Meta GenAI, I start to realize that the foundational models incorporate the knowledge of human skill, but still need customization so that they can be applied to the user’s current situation. What more straightforward way then egocentric visual perception?
English
1
0
0
45
Miao
Miao@aptx4869ml·
(3/n)we start to look at gaze, hand location/mask, 3D body, 3D scene… Yet, these representatives are still not ideal for skill transfer, as users would want something can be easily interpreted, like the instructions from the LEGO, but with more customized to user setting.
English
1
0
0
41
Miao
Miao@aptx4869ml·
(1/n)When I first started my PhD with Jim, one thing we keep talking about is leveraging egocentric vision for skill transfer, to help robot or human to solve the howto problem.
English
1
0
0
43
Miao
Miao@aptx4869ml·
Wonderful job from Bolin! I want to provide some story behind the scenes.
English
1
0
4
171
Miao retweetledi
Bolin Lai
Bolin Lai@bryanislucky·
Our paper was awarded the Best Student Paper Prize in BMVC2022🎉 Thanks for my advisor @RehgJim and all co-authors @aptx4869ml @fionakryan. Now we have released our data, codes and pretrained weights on GitHub (github.com/BolinLai/GLC) as well as a video demo on the project page.
Bolin Lai tweet mediaBolin Lai tweet media
English
1
8
16
2.6K
Miao retweetledi
Zhaoyang Lv
Zhaoyang Lv@LvZhaoyang·
Our team at RLR is hosting a @CVPR tutorial for always-on egocentric vision research using Project Aria on this coming Sunday afternoon. Together with tutorial, we also released the first Project Aria Pilot Dataset and data tools. Tutorial page: ariatutorial2022.github.io
GIF
English
3
8
71
0
Miao retweetledi
AI at Meta
AI at Meta@AIatMeta·
Join the #Ego4D challenge, exploring the largest ever dataset of first-person video and five new research benchmarks: episodic memory, hands+objects, social, AV, forecasting. First round of the competition ends June 1 with results shared at #CVPR. ego4d-data.org/docs/challenge/
English
10
22
79
0
Miao retweetledi
Stefan Stojanov
Stefan Stojanov@sstj389·
A new year, a new shameless twitter plug: Check out our Toys4K 3D object dataset 4K instances, 105 categories, 15+ instances per category github.com/rehg-lab/lowsh…
GIF
English
0
12
62
0

Keşfet

@Yihe_yihe @JiashuXu2 @ChengshuEricLi @Wensi @Monalissome @Koven_Yu @josiah_is_wong @sanjana__z