Runtime error
Agents
Video Action Recognition On MERL Shopping Dataset
📊
Video action recognition task with V-JEPA2 model
Chanyong Shin
scyonggg
AI & ML interests
Computer Vision //
Vision Language Model (VLM) //
Segmentation //
Transformer Architecture //
Embedded Vision //
FPGA //
Light-weight Deep Learning //
Frame Interpolation
Recent Activity
upvoted a paper 11 days ago
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini upvoted a paper 25 days ago
GCC: Generative Color Constancy via Diffusing a Color Checker