hmdb51

There are 1 repository under hmdb51 topic.

MichiganCOG / ViP
Video Platform for Action Recognition and Object Detection in Pytorch
action-recognition c3d deep-learning detection dhf1k dvsa hmdb51 i3d imagenetvid mscoco neural-networks object-detection pytorch resnet ssd ucf101 video-platform video-saliency ycbb youcook
Language:Python 221
kevin-ssy / Optical-Flow-Guided-Feature
Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018
action-recognition deep-learning hmdb51 motion-design ucf101 video-classification
Language:C++ 196
bryanyzhu / Hidden-Two-Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
action-recognition caffe cnn hmdb51 optical-flow real-time ucf101 unsupervised-learning video
Language:C++ 194
csiro-robotics / TCE
This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
self-supervised-learning computer-vision contrastive-learning metric-learning representation-learning ucf-101 pytorch hmdb51 kinetics-datasets action-recognition tsne-visualisations contrastive-loss embeddings deep-learning
Language:Python 52
sjenni / temporal-ssl
Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.
self-supervised-learning action-recognition tensorflow ucf101 hmdb51 unsupervised-learning c3d transfer-learning
Language:Python 48
vra / action-recognition-using-3d-resnet
Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.
action-recognition 3d-resnet ucf101 hmdb51 deep-learning cnn extract-features
Language:Python 41
pritamqu / CrissCross
[AAAI 2023 (Oral)] CrissCross: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
self-supervised-learning action-recognition kinetics400 audioset kinetics-datasets ucf101 hmdb51 sound-classification esc50 representation-learning dcase
Language:Python 24
MSQNet
mondalanindya / MSQNet
Actor-agnostic Multi-label Action Recognition with Multi-modal Query [ICCVW '23]
action-recognition animal-behavior charades hmdb51 video-representation-learning vision-and-language vision-language vision-transformer zero-shot-classification
Language:Python 23
milkcat0904 / video-dataset-to-optical-flow
由视频数据集生成optical flow，frames，warped flow
optical-flow ucf101 hmdb51
Language:C++ 20
wgcban / apt
PyTorch Implementation of Attention Prompt Tuning: Parameter-Efficient Adaptation of Pre-Trained Models for Action Recognition
adapter-tuning computer-vision hmdb51 linear-probing prompt-tuning something-something tuning-parameters ucf-101 video-understanding
Language:Python 14
hmdb51-two-stream-action-recognition
giocoal / hmdb51-two-stream-action-recognition
Two-stream CNNs for Video Action Recognition using Stacked Optical Flow. Implemented in Keras on HMDB-51 dataset.
action-recognition hmdb hmdb51 keras keras-tensorflow opencv optical-flow python resnet-50 two-stream two-stream-cnn video-recognition
Language:Python 13
pritamqu / XKD
[AAAI 2024] XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning.
hmdb51 kinetics400 self-supervised-learning ucf101 video-learning
Language:Python 12
ahkarami / T3D
Temporal 3D ConvNet
3d-convolutional-network temporal-pooling video-classification action-recognition activity-recognition pytorch 3d-cnn temporal-3d-convnet temporal-transition-layer sports-1m ucf101 hmdb51 kinetics
Language:Python 9
titania7777 / VideoFrameSampler
Salient Video Frames Sampling Method Using the Mean of Deep Features for Efficient Model Training (KIBME 2021)
pytorch video-frame-sampler efficient-training video-analytics ucf101 hmdb51 activitynet
Language:Python 6
Action_Recognition_Two_Stream_HMDB51
gianscuri / Action_Recognition_Two_Stream_HMDB51
Action Recognition using a two stream CNN architecture with Frames and Optical Flows. Realized using Keras on HMDB51 dataset.
action-recognition cnn computer-vision hmdb51 keras
Language:Jupyter Notebook 3
JohnPPinto / HMDB51_human_motion_recognition_pytorch
A project on video classification using PyTorch 2.0.
deep-learning gradio hmdb51 huggingface lighning-fabric pytorch pytorch-lightning video-classification
Language:Jupyter Notebook 2
LoreImbo / hmdb51-video-classification
Human Activity Recognition (HAR) using LRCN approach and MoveNet approach on HMDB-51 dataset
deep-learning hmdb51 human-activity-recognition keras-tensorflow python
Language:Jupyter Notebook 2
malswadi / skeleton-ucf-hmdb
This is the project repository for the research study "Skeleton-Split Framework using Spatial Temporal Graph Convolutional Networks for Action Recognition" presented by Motasem S. Alsawadi and Miguel Rio.
skeleton ucf-101 hmdb51
2
reshalfahsi / action-recognition
Action Recognition Using CNN + Bidirectional RNN
action-recognition computer-vision pytorch pytorch-lightning video-classification bidirectional-rnn mnasnet cnn hmdb51 video-processing
Language:Jupyter Notebook