yyuncong/TempCLR
[ICLR 2023] Temporal Alignment Representations with Contrastive Learning
This project helps machine learning researchers improve how computers understand the sequence of actions in a video, like steps in a recipe or instructions. It takes raw video and text descriptions as input and produces models that can better align visual events with their corresponding textual explanations. Researchers working on video analysis, action recognition, or multimodal learning would find this useful.
No commits in the last 6 months.
Use this if you are a machine learning researcher aiming to build or evaluate models that understand and align temporal information in videos with accompanying text, especially for tasks like action step localization or video retrieval.
Not ideal if you are looking for a ready-to-use application for end-users or if your primary interest is not in developing and researching video-text alignment algorithms.
Stars
27
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yyuncong/TempCLR"
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