Vongani Maluleke
@vonekels
Followers
341
Following
151
Media
37
Statuses
131
🇿🇦 || AI Graduate Researcher @berkeley_ai || Advisors: @JitendraMalikCV and @akanazawa || Research Interest: AI for social good, 3D Vision, and GANs.
Berkeley, California
Joined August 2013
To what extent does social interaction affect behavior in couples swing dancing?. Our work looks at how we can predict a dancer's next moves based on their past motion alone or by considering both the dancer's and their partner's motions. 🪩🕺🏾 🆚 🪩🕺🏾💃🏾. 🧵1/6
10
24
115
Thanks @lisabdunlap for organizing a long overdue talk. -----Biltong Vs Beef Jerky Poll Results------.They came. They chewed. They voted. Biltong got 75% — Swi nandzika ngopfu!!
Why have a dissertation when you can have a DESSERTation? Thanks to @vonekels for co leading this joke talk and our advisors @profjoeyg and @akanazawa for introducing us just like a real dissertation (although to be fair Joey thought this was my actual defense)
0
1
7
RT @brenthyi: We wrote a paper: estimating body and hand motion from a pair of glasses! 👓. website: code: https://t….
0
119
0
Please see the website for more details. synNsync🪩is joint work with my awesome ✨co-authors✨:.@LeaMue27 @brjathu @geopavlakos @shiryginosar @akanazawa @JitendraMalikCV. Website🖥️: Data💾: Arxiv📜: 🧵6/6.
0
1
25
Sampling multiple predictions👯👯👯 from our model shows that knowing about the "other" helps generate diverse motion that is closer to the ground truth. 🧵5/6
1
0
3
Conditioned on past dyadic motions of Alice and Bob 🪩🕺🏾💃🏾, our method can predict plausible and realistic motions better than the case where you only have Alice's past motion, i.e. unary case🪩🕺🏾. 🧵4/6
1
0
4
We used a combination of VQ-VAE and autoregressive architecture to predict 🔮the next set of tokens in the motion sequence representing the 4D humans. ▶️🪩🕺🏾💃🏾⏭️💃🏾⏭️💃🏾⏭️💃🏾⏭️💃🏾. 🧵3/6
1
0
2
We created an in-the-wild Swing Dance dataset 🪩 to study this. We lift the video into 4D using SLAHMR to extract 3D human motion in the world from 680 unique videos. The dataset features about 30 hours of videos of Alice (Person A 🕺🏾) and Bob (Person B💃🏾). 🧵2/6
1
0
4
RT @geopavlakos: Super excited to share that I will be starting as an Assistant Professor at UT Austin @UTCompSci in January 2024! 🥳🥳. I'm….
0
11
0
RT @Michael_J_Black: While most existing methods that estimate 3D human pose and shape (HPS) do so in camera coordinates, many applications….
0
61
0
RT @akanazawa: I'll be talking about nerfstudio at #GTC2023 today at 2pm PT!. Come learn about #NeRFs, the latest updates in @nerfstudiotea….
0
10
0
RT @JitendraMalikCV: I delivered the 110th Annual Martin Meyerson UC Berkeley Faculty Research Lecture on March 20, 2023. .
0
24
0
RT @akanazawa: Psyched to finally release our new work that decouples human🧑🏽🤝🧑🏻 & camera motion🎥 from an unconstrained video✨ .We place….
0
88
0
RT @databoydg: Super proud of @vonekels and @neerjathakkar. Come check out some thought-provoking work at poster 43.
0
2
0
We’ll be presenting our Bias in GANs work at @eccvconf on 25/10 at 15:30. One of our findings ~ Truncation commonly used to improve image quality in GANs, decreases racial diversity of generated images. Paper link: #ECCV2022 @berkeley_ai @Berkeley_EECS
0
18
51
RT @AdemiAdeniji: Excited to announce Intrinsic Reward Matching (IRM) - a novel and efficient algorithmic framework unifying unsupervised R….
0
52
0
🎊🎊New Paper Alert!!!🎊🎊: Studying Bias Through the Lens of Race.
Our ECCV ‘22 paper “Studying Bias in GANs Through the Lens of Race” is now out! This work was done with @vonekels, @databoydg, @akanazawa, @trevordarrell, @ethanjweber, Tim Brooks and Alyosha Efros (1/n).
1
3
18