Highlights
- Pro
Pinned Loading
-
TrafficVLM
TrafficVLM Public[CVPRW 2024] TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning. Official code for the 3rd place solution of the AI City Challenge 2024 Track 2.
-
Dual-Vehicle-Aug-Symmetric-Net
Dual-Vehicle-Aug-Symmetric-Net PublicForked from Lighthouse-Association/Dual-Vehicle-Aug-Symmetric-Net
The 7th place solution of the 7th AI City Challenge Track 2.
Jupyter Notebook 1
-
DiffLM-Control-Style-Transfering
DiffLM-Control-Style-Transfering PublicA continuous diffusion language model for sequence-to-sequence tasks that uses a pretrained BERT model for word embedding.
-
mediapipe-face-emotion-detection
mediapipe-face-emotion-detection PublicFace emotion detection using MediaPipe and angular encoding
Jupyter Notebook
-
Virtual-Ring-TryOn
Virtual-Ring-TryOn PublicAn application of AR technology in trying clothes and jewellery in Vietnam.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.