minghangz/cpl
CPL: Weakly Supervised Temporal Sentence Grounding with Gaussian-based Contrastive Proposal Learning
This tool helps video analysts and content creators quickly pinpoint specific moments in long videos by simply describing what they're looking for in a sentence. You provide a video and a text description, and it outputs the exact start and end times in the video where that described event occurs. This is ideal for anyone working with extensive video footage who needs to efficiently locate particular actions or scenes.
No commits in the last 6 months.
Use this if you need to precisely locate specific events within long video files using a natural language description, without manually scrubbing through hours of footage.
Not ideal if your videos are short, lack diverse events, or if you prefer manual annotation over automated temporal grounding.
Stars
65
Forks
5
Language
Python
License
—
Category
Last pushed
Apr 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/minghangz/cpl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification