Haiyang Liu

H-Liu1997's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in H-Liu1997/TANGO 26 days ago

help wanted, build error

3

#20 opened 26 days ago by

H-Liu1997

updated a Space 29 days ago

Build error

335

335

TANGO

🐠

Co-Speech Gesture Video Generation

liked a Space 2 months ago

Running on Zero

3

3

SynTalker

🏆

A web demo of SynTalker

updated a Space 2 months ago

Running on T4

64

64

EMAGE

🐑

Co-Speech 3D Gesture Generation

updated 3 datasets 2 months ago

H-Liu1997/BEAT2_Tools

Updated Jan 6 • 201

H-Liu1997/BEAT

Viewer • Updated Jan 6 • 1.1k • 74

H-Liu1997/BEAT_Rendered_Videos

Viewer • Updated Jan 6 • 667 • 1.55k

updated 3 models 2 months ago

H-Liu1997/emage_evaltools

Updated Jan 6

H-Liu1997/disco_audio

Updated Jan 3 • 509

H-Liu1997/emage_audio

Updated Jan 2 • 932

updated a model 3 months ago

H-Liu1997/camn_audio

Updated Dec 13, 2024 • 1.48k

upvoted 2 papers 4 months ago

TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation

Paper • 2410.04221 • Published Oct 5, 2024 • 3

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

Paper • 2401.00374 • Published Dec 31, 2023 • 1

New activity in H-Liu1997/TANGO 4 months ago

Does this method support audio input in other languages, such as Chinese？Thanks!

1

#19 opened 4 months ago by

wxd00

New activity in H-Liu1997/EMAGE 4 months ago

H-Liu1997

1

#1 opened 4 months ago by

PeepDaSlan9

New activity in H-Liu1997/TANGO 5 months ago

Do the method supports other language

2

#16 opened 5 months ago by

wxd00

Quality of video is not very high

1

#14 opened 5 months ago by

rajatgarg79

Random gestures during silences

1

#15 opened 5 months ago by

ved17ansh

authored 2 papers 5 months ago

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

Paper • 2401.00374 • Published Dec 31, 2023 • 1

TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation

Paper • 2410.04221 • Published Oct 5, 2024 • 3