Seongchan Kim

Seongchan's activity

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

upvoted a paper about 1 month ago

Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

Paper • 2510.23581 • Published Oct 27 • 41

authored 3 papers 2 months ago

Multi-Granularity Video Object Segmentation

Paper • 2412.01471 • Published Dec 2, 2024

InterRVOS: Interaction-aware Referring Video Object Segmentation

Paper • 2506.02356 • Published Jun 3

MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Paper • 2510.07310 • Published Oct 8 • 35

upvoted a paper 2 months ago

MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Paper • 2510.07310 • Published Oct 8 • 35

liked a model 5 months ago

ByteDance/Sa2VA-1B

Image-Text-to-Text • 1B • Updated Sep 8 • 630 • 29

upvoted a paper 6 months ago

Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation

Paper • 2506.11924 • Published Jun 13 • 34

liked 8 datasets 8 months ago

turing-motors/CoVLA-Dataset

Viewer • Updated Mar 1 • 10k • 3.05k • 41

WenhaoWang/VidProM

Viewer • Updated Jun 19 • 1.67M • 18.9k • 75

ShareGPT4Video/ShareGPT4Video

Viewer • Updated Mar 7 • 40.2k • 1.65k • 200

lmms-lab/LLaVA-Video-178K

Viewer • Updated Oct 11, 2024 • 1.63M • 33.7k • 179

open-social-world/EgoNormia

Viewer • Updated Jun 11 • 1.74k • 1.2k • 4

nkp37/OpenVid-1M

Viewer • Updated Jul 14 • 1.45M • 28k • 238

Antreas/TALI

Viewer • Updated Dec 13, 2023 • 1.17M • 3.67k • 15

lmms-lab/Video-MME

Viewer • Updated Jul 4, 2024 • 2.7k • 26.3k • 60

upvoted a paper 8 months ago

URECA: Unique Region Caption Anything

Paper • 2504.05305 • Published Apr 7 • 35

upvoted a paper 9 months ago

A Noise is Worth Diffusion Guidance

Paper • 2412.03895 • Published Dec 5, 2024 • 30

liked a dataset 11 months ago

SammyLim/MUG-VOS

Preview • Updated Dec 20, 2024 • 718 • 2

liked a model over 1 year ago

hyoungwoncho/sd_perturbed_attention_guidance_controlnet

Image-to-Image • Updated Apr 22, 2024 • 3