[ { "3-fold Accuracy": 98, "code_links": [ { "title": "deepmind/kinetics-i3d", "url": "https://github.com/deepmind/kinetics-i3d" }, { "title": "piergiaj/pytorch-i3d", "url": "https://github.com/piergiaj/pytorch-i3d" }, { "title": "yaohungt/GSTEG_CVPR_2019", "url": "https://github.com/yaohungt/GSTEG_CVPR_2019" }, { "title": "dlpbc/keras-kinetics-i3d", "url": "https://github.com/dlpbc/keras-kinetics-i3d" }, { "title": "FrederikSchorr/sign-language", "url": "https://github.com/FrederikSchorr/sign-language" }, { "title": "OanaIgnat/i3d_keras", "url": "https://github.com/OanaIgnat/i3d_keras" }, { "title": "ahsaniqbal/Kinetics-FeatureExtractor", "url": "https://github.com/ahsaniqbal/Kinetics-FeatureExtractor" }, { "title": "novav/CV_Spatiotemporal_Feature_3D_CNN", "url": "https://github.com/novav/CV_Spatiotemporal_Feature_3D_CNN" }, { "title": "sebastiantiesmeyer/deeplabchop3d", "url": "https://github.com/sebastiantiesmeyer/deeplabchop3d" }, { "title": "vijayvee/behavior-recognition", "url": "https://github.com/vijayvee/behavior-recognition" }, { "title": "vijayvee/behavior_recognition", "url": "https://github.com/vijayvee/behavior_recognition" }, { "title": "AbdurrahmanNadi/activity_recognition_web_service", "url": "https://github.com/AbdurrahmanNadi/activity_recognition_web_service" }, { "title": "Alexyuda/action_recognition", "url": "https://github.com/Alexyuda/action_recognition" } ], "date": "2017-05-22", "date2": 20170522, "model": "Two-stream I3D (on pre-trained)", "paper": { "title": "Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset", "url": "https://cknow.io/lib/e93903d8f34491a9" }, "paper_data_uoa": "e93903d8f34491a9" }, { "3-fold Accuracy": 97.8, "code_links": [ { "title": "craston/MARS", "url": "https://github.com/craston/MARS" } ], "date": "2019-06-01", "date2": 20190601, "model": "MARS+RGB+Flow (64 frames, Kinetics pretrained)", "paper": { "title": "MARS: Motion-Augmented RGB Stream for Action Recognition", "url": "https://cknow.io/lib/e917d94a27b04d45" }, "paper_data_uoa": "e917d94a27b04d45" }, { "3-fold Accuracy": 97.7, "code_links": [ { "title": "holistic-video-understanding/Mini-HVU", "url": "https://github.com/holistic-video-understanding/Mini-HVU" }, { "title": "holistic-video-understanding/HVU-Dataset", "url": "https://github.com/holistic-video-understanding/HVU-Dataset" } ], "date": "2019-04-25", "date2": 20190425, "model": "HATNet (32 frames, HVU pretrained)", "paper": { "title": "Large Scale Holistic Video Understanding", "url": "https://cknow.io/lib/5b16b09584bdea1a" }, "paper_data_uoa": "5b16b09584bdea1a" }, { "3-fold Accuracy": 97.4, "code_links": [], "date": "2019-08-27", "date2": 20190827, "model": "CCS + TSN (ImageNet+Kinetics pretrained)", "paper": { "title": "Cooperative Cross-Stream Network for Discriminative Action Representation", "url": "https://cknow.io/lib/09a74f888e9817da" }, "paper_data_uoa": "09a74f888e9817da" }, { "3-fold Accuracy": 97.2, "code_links": [], "date": "2019-03-20", "date2": 20190320, "model": "Multi-stream I3D ", "paper": { "title": "Contextual Action Cues from Camera Sensor for Multi-Stream Action Recognition", "url": "https://cknow.io/lib/e85e30290a1982be" }, "paper_data_uoa": "e85e30290a1982be" }, { "3-fold Accuracy": 97.1, "code_links": [ { "title": "bryanyzhu/two-stream-pytorch", "url": "https://github.com/bryanyzhu/two-stream-pytorch" }, { "title": "bryanyzhu/Hidden-Two-Stream", "url": "https://github.com/bryanyzhu/Hidden-Two-Stream" }, { "title": "AbdalaDiasse/Video-classification-for-oil-quality-estimation", "url": "https://github.com/AbdalaDiasse/Video-classification-for-oil-quality-estimation" } ], "date": "2017-04-02", "date2": 20170402, "model": "Hidden Two-Stream", "paper": { "title": "Hidden Two-Stream Convolutional Networks for Action Recognition", "url": "https://cknow.io/lib/1b3bdadb4a42b57d" }, "paper_data_uoa": "1b3bdadb4a42b57d" }, { "3-fold Accuracy": 96.5, "code_links": [], "date": "2019-08-01", "date2": 20190801, "model": "CMA iter1-S", "paper": { "title": "Two-Stream Video Classification with Cross-Modality Attention", "url": "https://cknow.io/lib/4941b9bf95ce83e5" }, "paper_data_uoa": "4941b9bf95ce83e5" }, { "3-fold Accuracy": 96.2, "code_links": [], "date": "2019-08-07", "date2": 20190807, "model": "STM (ImageNet+Kinetics pretrain)", "paper": { "title": "STM: SpatioTemporal and Motion Encoding for Action Recognition", "url": "https://cknow.io/lib/dbf65072610598a3" }, "paper_data_uoa": "dbf65072610598a3" }, { "3-fold Accuracy": 95.8, "code_links": [ { "title": "craston/MARS", "url": "https://github.com/craston/MARS" } ], "date": "2019-06-01", "date2": 20190601, "model": "MARS+RGB+Flow (16 frames)", "paper": { "title": "MARS: Motion-Augmented RGB Stream for Action Recognition", "url": "https://cknow.io/lib/e917d94a27b04d45" }, "paper_data_uoa": "e917d94a27b04d45" }, { "3-fold Accuracy": 95.7, "code_links": [], "date": "2019-04-05", "date2": 20190405, "model": "Prob-Distill", "paper": { "title": "Paying More Attention to Motion: Attention Distillation for Learning Video Representations", "url": "https://cknow.io/lib/b222433297a9a5c3" }, "paper_data_uoa": "b222433297a9a5c3" }, { "3-fold Accuracy": 95.1, "code_links": [], "date": "2019-08-09", "date2": 20190809, "model": "I3D-LSTM", "paper": { "title": "I3D-LSTM: A New Model for Human Action Recognition", "url": "https://cknow.io/lib/24ed1b3095ea1059" }, "paper_data_uoa": "24ed1b3095ea1059" }, { "3-fold Accuracy": 94.5, "code_links": [ { "title": "kenshohara/3D-ResNets-PyTorch", "url": "https://github.com/kenshohara/3D-ResNets-PyTorch" }, { "title": "kenshohara/video-classification-3d-cnn-pytorch", "url": "https://github.com/kenshohara/video-classification-3d-cnn-pytorch" }, { "title": "okankop/Efficient-3DCNNs", "url": "https://github.com/okankop/Efficient-3DCNNs" }, { "title": "kenshohara/3D-ResNets", "url": "https://github.com/kenshohara/3D-ResNets" }, { "title": "sebastiantiesmeyer/deeplabchop3d", "url": "https://github.com/sebastiantiesmeyer/deeplabchop3d" }, { "title": "ankitshah009/unsupervised_video_retrieval_from_activity", "url": "https://github.com/ankitshah009/unsupervised_video_retrieval_from_activity" }, { "title": "carVaba/video-classification-3d-cnn-pytorch", "url": "https://github.com/carVaba/video-classification-3d-cnn-pytorch" }, { "title": "LiliMeng/3D-ResNets-Pytorch-ImageNet-Moments", "url": "https://github.com/LiliMeng/3D-ResNets-Pytorch-ImageNet-Moments" }, { "title": "Xiehuaiqi/3D-ResNets-PyTorch-master", "url": "https://github.com/Xiehuaiqi/3D-ResNets-PyTorch-master" }, { "title": "concordiaca/3D-ResNets-PyTorch", "url": "https://github.com/concordiaca/3D-ResNets-PyTorch" }, { "title": "kaiqiangh/extracting-video-features-ResNeXt", "url": "https://github.com/kaiqiangh/extracting-video-features-ResNeXt" }, { "title": "nCheck/video-class-3d-resnet", "url": "https://github.com/nCheck/video-class-3d-resnet" }, { "title": "dongzhuoyao/3D-ResNets-PyTorch", "url": "https://github.com/dongzhuoyao/3D-ResNets-PyTorch" }, { "title": "ptmcgrat/3D-Resnets", "url": "https://github.com/ptmcgrat/3D-Resnets" }, { "title": "qwarts/video_classification", "url": "https://github.com/qwarts/video_classification" }, { "title": "LiliMeng/3D-ResNets-PyTorch", "url": "https://github.com/LiliMeng/3D-ResNets-PyTorch" }, { "title": "arundhatikurup/3DResnet", "url": "https://github.com/arundhatikurup/3DResnet" }, { "title": "ptmcgrat/3D-ResNets-PyTorch", "url": "https://github.com/ptmcgrat/3D-ResNets-PyTorch" }, { "title": "danielmatte/3D-ResNets-PyTorch-", "url": "https://github.com/danielmatte/3D-ResNets-PyTorch-" }, { "title": "skamdar/gesture_recognition", "url": "https://github.com/skamdar/gesture_recognition" } ], "date": "2017-11-27", "date2": 20171127, "model": "ResNeXt-101 (64f)", "paper": { "title": "Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?", "url": "https://cknow.io/lib/0970174815530459" }, "paper_data_uoa": "0970174815530459" }, { "3-fold Accuracy": 94.5, "code_links": [], "date": "2019-06-19", "date2": 20190619, "model": "R-STAN-101", "paper": { "title": "R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition", "url": "https://cknow.io/lib/1c94b929dfcdb35e" }, "paper_data_uoa": "1c94b929dfcdb35e" }, { "3-fold Accuracy": 94.3, "code_links": [], "date": "2018-09-11", "date2": 20180911, "model": "TSN+TSM", "paper": { "title": "Temporal-Spatial Mapping for Action Recognition", "url": "https://cknow.io/lib/f1e4152a05f691e9" }, "paper_data_uoa": "f1e4152a05f691e9" }, { "3-fold Accuracy": 93.4, "code_links": [ { "title": "deepmind/kinetics-i3d", "url": "https://github.com/deepmind/kinetics-i3d" }, { "title": "piergiaj/pytorch-i3d", "url": "https://github.com/piergiaj/pytorch-i3d" }, { "title": "yaohungt/GSTEG_CVPR_2019", "url": "https://github.com/yaohungt/GSTEG_CVPR_2019" }, { "title": "dlpbc/keras-kinetics-i3d", "url": "https://github.com/dlpbc/keras-kinetics-i3d" }, { "title": "FrederikSchorr/sign-language", "url": "https://github.com/FrederikSchorr/sign-language" }, { "title": "OanaIgnat/i3d_keras", "url": "https://github.com/OanaIgnat/i3d_keras" }, { "title": "ahsaniqbal/Kinetics-FeatureExtractor", "url": "https://github.com/ahsaniqbal/Kinetics-FeatureExtractor" }, { "title": "novav/CV_Spatiotemporal_Feature_3D_CNN", "url": "https://github.com/novav/CV_Spatiotemporal_Feature_3D_CNN" }, { "title": "sebastiantiesmeyer/deeplabchop3d", "url": "https://github.com/sebastiantiesmeyer/deeplabchop3d" }, { "title": "vijayvee/behavior-recognition", "url": "https://github.com/vijayvee/behavior-recognition" }, { "title": "vijayvee/behavior_recognition", "url": "https://github.com/vijayvee/behavior_recognition" }, { "title": "AbdurrahmanNadi/activity_recognition_web_service", "url": "https://github.com/AbdurrahmanNadi/activity_recognition_web_service" }, { "title": "Alexyuda/action_recognition", "url": "https://github.com/Alexyuda/action_recognition" } ], "date": "2017-05-22", "date2": 20170522, "model": "Two-stream I3D", "paper": { "title": "Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset", "url": "https://cknow.io/lib/e93903d8f34491a9" }, "paper_data_uoa": "e93903d8f34491a9" }, { "3-fold Accuracy": 91.5, "code_links": [], "date": "2019-06-19", "date2": 20190619, "model": "R-STAN-50", "paper": { "title": "R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition", "url": "https://cknow.io/lib/1c94b929dfcdb35e" }, "paper_data_uoa": "1c94b929dfcdb35e" }, { "3-fold Accuracy": 91.1, "code_links": [], "date": "2016-09-17", "date2": 20160917, "model": "MR Two-Sream R-CNN", "paper": { "title": "Multi-region two-stream R-CNN for action detection", "url": "https://cknow.io/lib/d4469b1efd718403" }, "paper_data_uoa": "d4469b1efd718403" }, { "3-fold Accuracy": 85.8, "code_links": [], "date": "2019-01-26", "date2": 20190126, "model": "R(2+1)D-18 (DistInit pretraining)", "paper": { "title": "DistInit: Learning Video Representations Without a Single Labeled Video", "url": "https://cknow.io/lib/a410b42da91f2d04" }, "paper_data_uoa": "a410b42da91f2d04" }, { "3-fold Accuracy": 74.94, "code_links": [ { "title": "okankop/Efficient-3DCNNs", "url": "https://github.com/okankop/Efficient-3DCNNs" } ], "date": "2019-04-04", "date2": 20190404, "model": "3D-SqueezeNet", "paper": { "title": "Resource Efficient 3D Convolutional Neural Networks", "url": "https://cknow.io/lib/c741b4dba4a608e4" }, "paper_data_uoa": "c741b4dba4a608e4" }, { "3-fold Accuracy": 65.4, "code_links": [], "date": "2014-06-23", "date2": 20140623, "model": "Slow Fusion + Finetune top 3 layers", "paper": { "title": "Large-Scale Video Classification with Convolutional Neural Networks", "url": "https://cknow.io/lib/df7f59b71147e88d" }, "paper_data_uoa": "df7f59b71147e88d" }, { "3-fold Accuracy": 63.27, "code_links": [], "date": "2019-09-11", "date2": 20190911, "model": "MLGCN", "paper": { "title": "MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition", "url": "https://cknow.io/lib/20ef35044a8a994d" }, "paper_data_uoa": "20ef35044a8a994d" }, { "3-fold Accuracy": 61.2, "code_links": [ { "title": "laura-wang/video_repres_mas", "url": "https://github.com/laura-wang/video_repres_mas" } ], "date": "2019-04-07", "date2": 20190407, "model": "Pretrained on Kinetics", "paper": { "title": "Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics", "url": "https://cknow.io/lib/510450184304f519" }, "paper_data_uoa": "510450184304f519" }, { "3-fold Accuracy": 56.52, "code_links": [ { "title": "okankop/Efficient-3DCNNs", "url": "https://github.com/okankop/Efficient-3DCNNs" } ], "date": "2019-04-04", "date2": 20190404, "model": "3D-ShuffleNetV2 0.25x", "paper": { "title": "Resource Efficient 3D Convolutional Neural Networks", "url": "https://cknow.io/lib/c741b4dba4a608e4" }, "paper_data_uoa": "c741b4dba4a608e4" }, { "3-fold Accuracy": 55.56, "code_links": [ { "title": "okankop/Efficient-3DCNNs", "url": "https://github.com/okankop/Efficient-3DCNNs" } ], "date": "2019-04-04", "date2": 20190404, "model": "3D-MobileNetV2 0.2x", "paper": { "title": "Resource Efficient 3D Convolutional Neural Networks", "url": "https://cknow.io/lib/c741b4dba4a608e4" }, "paper_data_uoa": "c741b4dba4a608e4" }, { "3-fold Accuracy": 43.9, "code_links": [ { "title": "ryanchesler/comma-speed-challenge", "url": "https://github.com/ryanchesler/comma-speed-challenge" }, { "title": "doronharitan/human_activity_recognition_LRCN", "url": "https://github.com/doronharitan/human_activity_recognition_LRCN" }, { "title": "Alexyuda/action_recognition", "url": "https://github.com/Alexyuda/action_recognition" }, { "title": "niveditarahurkar/CS231N-ActionRecognition", "url": "https://github.com/niveditarahurkar/CS231N-ActionRecognition" }, { "title": "rlaengud123/CMC_LRCN", "url": "https://github.com/rlaengud123/CMC_LRCN" } ], "date": "2012-12-03", "date2": 20121203, "model": "Baseline UCF101", "paper": { "title": "UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild", "url": "https://cknow.io/lib/41789e5cf2457780" }, "paper_data_uoa": "41789e5cf2457780" }, { "3-fold Accuracy": 42.5, "code_links": [], "date": "2018-03-22", "date2": 20180322, "model": "CD-UAR", "paper": { "title": "Towards Universal Representation for Unseen Action Recognition", "url": "https://cknow.io/lib/9c5347f4953a03dc" }, "paper_data_uoa": "9c5347f4953a03dc" }, { "3-fold Accuracy": 29.3, "code_links": [], "date": "2018-06-01", "date2": 20180601, "model": "I3D + PoTion", "paper": { "title": "PoTion: Pose MoTion Representation for Action Recognition", "url": "https://cknow.io/lib/8a812422fc8eff06" }, "paper_data_uoa": "8a812422fc8eff06" } ]