![Yanhong Zeng Profile](https://pbs.twimg.com/profile_images/1547875535996751872/rNZAL15X_x96.jpg)
Yanhong Zeng
@zengyh1900
Followers
234
Following
601
Statuses
66
Researcher in Shanghai AI Lab. Previously: PhD @MSFTResearch (MSRA) & SYSU.
Shanghai, China
Joined July 2022
😆 I absolutely love the generated manga about the Nobel Prize—so funny! This really shows how crucial datasets are! We put a lot of effort into building high-quality datasets for #manga generation. 📚✨ #AI #MangaArt
Thanks for your attention to our work. The code is also available. In addition, we also give an introduction video at youtube.
0
0
11
WOW!!! A GAME FROM NIJI 😍
🎩 ✨ Ready for an adventure? Join Tuxedo Cat as he wields dark magic to craft the ultimate bribe for Saika! No niji sub needed - anyone can help him out in this event! ✨⭐ 🎁 Win the exclusive Tuxedo Cat Fan Club badge and stand out in the Niji Discord with HALF A MILLION community members! 🚀 Stay tuned for more info tomorrow! 👀 #Nijijourney #TuxedoCat
1
1
11
RT @robrombach: 🔥 I am so damn excited to announce the launch of Black Forest Labs. We set ourselves on a mission to advance state-of-the-a…
0
156
0
Still just generating dance videos? Check the latest progress HumanVid in camera trajectory control and recreating classic movie shots 😍😍
Want to generate camera controllable human videos like a real movie clip? Try our HumanVid dataset and a baseline model combined by AnimateAnyone and CameraCtrl. Project Page: Paper: Data and code coming soon.
1
0
23
RT @XingangP: 📺Live Stream Translation via Uni-directional Attention Uni-directional Attention is common in LLMs. We study uni-directional…
0
3
0
BTW, ONE full registration can only cover ONE main conference paper 🥲 (CVPR allows to cover multiple papers
Baffling @eccvconf policy: Students cannot register their own paper, and must either rely on a non-student co-author's full registration, or must pay more money. Is the idea that we should be taxing students who write papers without faculty/industry support? Seems bad.
0
0
1
@skarlywarly @heartereum AMAZING! it might be hard to get even if it's released though 🥲🥲🥲 thanks for your reply
0
0
1
thank you for sharing! @AdeenaY8 😍Looking forward to more user cases and feedbacks from using #foleycrafter
FoleyCrafter 🔥 a video-to-audio generation framework from @OpenMMLab , which can produce realistic sound effects semantically relevant and synchronized with videos! Model: Demo: Paper: ✨ High-Quality Audio Generation: Ensures audio quality using a pre-trained text-to-audio model. ✨ Semantic Adapter: Aligns audio generation with video features through parallel cross-attention layers. ✨ Temporal Controller: Achieves precise audio-video synchronization with an onset detector and timestamp-based adapter. ✨ Text Prompt Compatibility: Supports controllable and diverse audio generation using text descriptions.
0
0
4