4.[Sparse 3D convolutional neural networks, BMVC 2015](http://arxiv.org/abs/1505.02890) SparseConvNets for 3D object recognition and (2+1)D video action recognition.
4.[Sparse 3D convolutional neural networks, BMVC 2015](http://arxiv.org/abs/1505.02890) SparseConvNets for 3D object recognition and (2+1)D video action recognition.
5.[Kaggle plankton recognition competition, 2015](https://www.kaggle.com/c/datasciencebowl) Third place. The competition solution is being adapted for research purposes in [EcoTaxa](http://ecotaxa.obs-vlfr.fr/).
5.[Kaggle plankton recognition competition, 2015](https://www.kaggle.com/c/datasciencebowl) Third place. The competition solution is being adapted for research purposes in [EcoTaxa](http://ecotaxa.obs-vlfr.fr/).
6.[Kaggle Diabetic Retinopathy Detection, 2015](https://www.kaggle.com/c/diabetic-retinopathy-detection/) First place in the Kaggle Diabetic Retinopathy Detection competition.
6.[Kaggle Diabetic Retinopathy Detection, 2015](https://www.kaggle.com/c/diabetic-retinopathy-detection/) First place in the Kaggle Diabetic Retinopathy Detection competition.
7.[Submanifold Sparse Convolutional Networks, 2017](https://arxiv.org/abs/1706.01307) Introduces deep 'submanifold' SparseConvNets.
7.[SparseConvNet 'classic'](https://github.com/btgraham/SparseConvNet-archived) version
8.[Workshop on Learning to See from 3D Data, 2017](https://shapenet.cs.stanford.edu/iccv17workshop/) First place in the [semantic segmentation](https://shapenet.cs.stanford.edu/iccv17/) competition. [Report](https://arxiv.org/pdf/1710.06104)
8.[Submanifold Sparse Convolutional Networks, 2017](https://arxiv.org/abs/1706.01307) Introduces deep 'submanifold' SparseConvNets.
9.[3D Semantic Segmentation with Submanifold Sparse Convolutional Networks, 2017](https://arxiv.org/abs/1711.10275) Semantic segmentation for the ShapeNet Core55 and NYU-DepthV2 datasets, CVPR 2018
9.[Workshop on Learning to See from 3D Data, 2017](https://shapenet.cs.stanford.edu/iccv17workshop/) First place in the [semantic segmentation](https://shapenet.cs.stanford.edu/iccv17/) competition. [Report](https://arxiv.org/pdf/1710.06104)
10.[Unsupervised learning with sparse space-and-time autoencoders](https://arxiv.org/abs/1811.10355)(3+1)D space-time autoencoders
10.[3D Semantic Segmentation with Submanifold Sparse Convolutional Networks, 2017](https://arxiv.org/abs/1711.10275) Semantic segmentation for the ShapeNet Core55 and NYU-DepthV2 datasets, CVPR 2018
11.[ScanNet 3D semantic label benchmark 2018](http://kaldir.vc.in.tum.de/scannet_benchmark/semantic_label_3d) 0.726 average IOU.
11.[Unsupervised learning with sparse space-and-time autoencoders](https://arxiv.org/abs/1811.10355)(3+1)D space-time autoencoders
12.[MinkowskiEngine](https://github.com/StanfordVL/MinkowskiEngine) is an alternative implementation of SparseConvNet; [0.736 average IOU for ScanNet](https://github.com/chrischoy/SpatioTemporalSegmentation).
12.[ScanNet 3D semantic label benchmark 2018](http://kaldir.vc.in.tum.de/scannet_benchmark/semantic_label_3d) 0.726 average IOU for 3D semantic segmentation.
13.[SpConv: PyTorch Spatially Sparse Convolution Library](https://github.com/traveller59/spconv) is an alternative implementation of SparseConvNet.
13.[MinkowskiEngine](https://github.com/StanfordVL/MinkowskiEngine) is an alternative implementation of SparseConvNet; [0.736 average IOU for ScanNet](https://github.com/chrischoy/SpatioTemporalSegmentation).
14.[Live Semantic 3D Perception for Immersive Augmented Reality](https://ieeexplore.ieee.org/document/8998140) describes a way to optimize memory access for SparseConvNet.
14.[SpConv: PyTorch Spatially Sparse Convolution Library](https://github.com/traveller59/spconv) is an alternative implementation of SparseConvNet.
15.[OccuSeg](https://arxiv.org/abs/2003.06537) real-time object detection using SparseConvNets.
15.[Live Semantic 3D Perception for Immersive Augmented Reality](https://ieeexplore.ieee.org/document/8998140) describes a way to optimize memory access for SparseConvNet.
16.[TorchSparse](https://github.com/mit-han-lab/torchsparse) implements 3D submanifold convolutions.
16.[OccuSeg](https://arxiv.org/abs/2003.06537) real-time object detection using SparseConvNets.
19.[VoTr](https://github.com/PointsCoder/VOTR) implements submanifold [voxel transformers](https://openaccess.thecvf.com/content/ICCV2021/papers/Mao_Voxel_Transformer_for_3D_Object_Detection_ICCV_2021_paper.pdf) using [SpConv](https://github.com/traveller59/spconv).
20.[Mix3D](https://github.com/kumuji/mix3d) brings [MixUp](https://openreview.net/forum?id=r1Ddp1-Rb) to the sparse setting—0.781 average IOU for ScanNet 3D semantic segmentation.
