Stars
Reliable, minimal and scalable library for pretraining foundation and world models
[NeurIPS 25] Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
[ICCV2025] SignRep: Enhancing Self-Supervised Sign Representations
[CVPR 2024] Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
Library for reading and processing ML training data.
A collection of learning resources for curious software engineers
Multi-modal zero-shot temporal action detection and localization
[CVPR 2023 Highlight & TPAMI] Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
The main contribution is to make self-supervised video representation learning more meaningful by raising awareness of motion data
Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline (CVPR 2023)
An efficient video loader for deep learning with smart shuffling that's super easy to digest
Implementation of the conjugate prior table for Bayesian Statistics
Fast linear assignment problem (LAP) solvers for Python based on c-extensions
Pytorch implementation of our T-PAMI 2021 paper: Self-supervised Video Representation Learning by Uncovering Motion and Appearance Statistics
Example code showing how to use Nvidia DALI in pytorch, with fallback to torchvision. Contains a few differences to the official Nvidia example, namely a completely CPU pipeline & improved memory u…
Federated Learning Benchmark - Federated Learning on Non-IID Data Silos: An Experimental Study (ICDE 2022)
Federated Optimization in Heterogeneous Networks (MLSys '20)
[CVPR 2021] Actor-Context-Actor Relation Network for Spatio-temporal Action Localization
Code for Personalized Federated Learning with Gaussian Processes
NNtrainer is Software Framework for Training and Inferencing Neural Network Models on Devices.
🔀 Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.