antoine77340 / Youtube-8M-WILLOW
Kaggle Youtube 8M WILLOW approach
☆465Updated last year
Related projects: ⓘ
- The 2nd place Solution to the Youtube-8M Video Understanding Challenge by Team Monkeytyping (based on tensorflow)☆176Updated 7 years ago
- Tensorflow toolbox implementing several learnable pooling architecture☆306Updated 6 years ago
- 1st place solution to Kaggle's 2018 YouTube-8M Video Understanding Challenge☆199Updated last year
- Code of PhoenixLin(3rd place) in the 2nd Youtube8M Video Understanding Challenge☆206Updated 5 years ago
- PaddlePaddle models for Youtube-8M Video Understanding Challenge☆113Updated 6 years ago
- AI Challenger, a platform for open datasets and programming competitions to artificial intelligence (AI) talents around the world.☆476Updated 3 years ago
- Pseudo-3D Convolutional Residual Networks for Video Representation Learning☆352Updated 5 years ago
- DenseNet Implementation in Tensorflow☆572Updated 5 years ago
- [CVPR 2018] End-to-End Learning of Motion Representation for Video Understanding☆289Updated 3 years ago
- A collection of recent video understanding datasets, under construction!☆454Updated 6 years ago
- ☆260Updated last year
- auto-tuning momentum SGD optimizer☆423Updated 6 years ago
- ☆492Updated this week
- Video Classification using 2 stream CNN☆310Updated 5 years ago
- Implementation of model compression with knowledge distilling method.☆344Updated 7 years ago
- Dual Path Networks☆537Updated 5 years ago
- Focal loss for Dense Object Detection☆483Updated 6 years ago
- Demonstrate the finetune process on TensorFlow☆131Updated 5 years ago
- InceptionV3, InceptionV4, Inception-Resnet pretrained models for Torch7 and PyTorch☆290Updated last year
- The implementation of focal loss proposed on "Focal Loss for Dense Object Detection" by KM He and support for multi-label dataset.☆314Updated 6 years ago
- RFCN implementation in TensorFlow☆291Updated 6 years ago
- Lisa Anne's public caffe code.☆220Updated 7 years ago
- Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018☆436Updated 5 years ago
- OHEM support for Fast R-CNN☆422Updated 6 years ago
- Segment-CNN: A Framework for Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs☆235Updated 5 years ago
- Detectorch - detectron for PyTorch☆559Updated 5 years ago
- The pretrained models trained on Moments in Time Dataset☆355Updated 3 years ago
- A fork of Caffe with OpenMPI-based Multi-GPU (mainly data parallel) support for action recognition and more. More documentation please se…☆551Updated 6 years ago
- Repo about neural networks for images handling☆265Updated 6 years ago
- ☆506Updated 4 years ago