Pinned Repositories
ICML2024-OT-CLIP
Official Repository for ICML 2024 Paper "OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport"
KING
Evaluating the smooth tracking and consistent generation of entities in motion within diffused videos.
Latte
Latte: Latent Diffusion Transformer for Video Generation.
mindone
one for all, Optimal generator with No Exception
Open-Sora
ssl-optimal-transport
SVIP-Smooth-DTW
Sequence Verification for Procedures in Videos With Smooth DTW Loss
tcformer-vitpose-ensemble-annotator
An annotation tool that combines TCFormer and ViTPose as an ensemble setup for COCO Wholebody annotations.
yolov5-vitpose-video-annotator
Simple pipeline using Yolov5 and ViTPose to annotate human pose in videos.
yolov7-pose-whole-body
Yolov7-pose with variable keypoint support. Trained models with COCO Wholebody.
fan23j's Repositories
fan23j/ICML2024-OT-CLIP
Official Repository for ICML 2024 Paper "OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport"
fan23j/yolov7-pose-whole-body
Yolov7-pose with variable keypoint support. Trained models with COCO Wholebody.
fan23j/yolov5-vitpose-video-annotator
Simple pipeline using Yolov5 and ViTPose to annotate human pose in videos.
fan23j/Open-Sora
fan23j/KING
Evaluating the smooth tracking and consistent generation of entities in motion within diffused videos.
fan23j/Latte
Latte: Latent Diffusion Transformer for Video Generation.
fan23j/mindone
one for all, Optimal generator with No Exception
fan23j/ssl-optimal-transport
fan23j/SVIP-Smooth-DTW
Sequence Verification for Procedures in Videos With Smooth DTW Loss
fan23j/tcformer-vitpose-ensemble-annotator
An annotation tool that combines TCFormer and ViTPose as an ensemble setup for COCO Wholebody annotations.
fan23j/TCM
Turning a CLIP Model into a Scene Text Detector (CVPR2023)