ActivityNet
ActivityNet solver
An implementation of the 2016 ActivityNet action recognition challenge using a CNN + LSTM approach with multi-threaded loading.
2016 ActivityNet action recognition challenge. CNN + LSTM approach. Multi-threaded loading.
54 stars
3 watching
14 forks
Language: Lua
last commit: over 8 years ago
Linked from 1 awesome list
carpedm20/awesome-torchRelated projects:
| Repository | Description | Stars |
|---|---|---|
 guillaume-chevalier/har-stacked-residual-bidir-lstms | An implementation of a deep neural network architecture for Human Activity Recognition using stacked residual bidirectional LSTM cells with TensorFlow. | 319 |
 pistony/residualattentionnetwork | A Gluon implementation of Residual Attention Network for image classification tasks | 107 |
 michigancog/m-pact | A framework for building and testing activity recognition models using deep learning techniques. | 107 |
 karandwivedi42/imagenet-multigpu.torchnet | A Lua-based implementation of a multi-GPU training framework for image classification using the Alexnet model. | 4 |
 liyuanlucasliu/ld-net | A system for efficiently training and deploying neural networks for named entity recognition tasks with context-dependent representations. | 146 |
 lz118/deep-correlation-network | Develops a deep neural network model for detecting salient objects in RGBT images using correlation information from other colors. | 13 |
 4uiiurz1/pytorch-res2net | Implementations of deep learning architectures using PyTorch for image classification tasks on various datasets. | 112 |
 microsoft/archai | Automates the search for optimal neural network configurations in deep learning applications | 467 |
 vlgiitr/dmn-plus | A PyTorch implementation of an improved question answering architecture with dynamic memory networks and attention mechanisms | 64 |
 oyxhust/cnn-lstm-ctc-text-recognition | Develops CTC-based text recognition models with neural network architectures | 259 |
 nust-machine-intelligence-laboratory/jo-src | An implementation of a contrastive learning approach to address noisy labels in machine learning models | 5 |
 andreas-bulling/actrectut | A toolkit providing a framework and tools for designing and evaluating activity recognition systems using inertial sensors. | 56 |
 mrkn/mxnet.rb | A Ruby interface to MXNet's deep learning framework | 48 |
 clementfarabet/lua---nnx | An extension to Torch7's neural network package with experimental modules and optimizations. | 97 |
 zhiwu-huang/lienet | This project uses deep learning and Lie group theory to recognize actions from skeleton data | 64 |