Action Recognition Using CNN + Bidirectional RNN
-
Updated
Jan 23, 2024 - Jupyter Notebook
Action Recognition Using CNN + Bidirectional RNN
A project on video classification using PyTorch 2.0.
Human Activity Recognition (HAR) using LRCN approach and MoveNet approach on HMDB-51 dataset
Action Recognition using a two stream CNN architecture with Frames and Optical Flows. Realized using Keras on HMDB51 dataset.
Salient Video Frames Sampling Method Using the Mean of Deep Features for Efficient Model Training (KIBME 2021)
[AAAI 2024] XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning.
Temporal 3D ConvNet
Two-stream CNNs for Video Action Recognition using Stacked Optical Flow. Implemented in Keras on HMDB-51 dataset.
PyTorch Implementation of Attention Prompt Tuning: Parameter-Efficient Adaptation of Pre-Trained Models for Action Recognition
Actor-agnostic Multi-label Action Recognition with Multi-modal Query [ICCVW '23]
[AAAI 2023 (Oral)] CrissCross: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.
Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.
This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018
Video Platform for Action Recognition and Object Detection in Pytorch
Add a description, image, and links to the hmdb51 topic page so that developers can more easily learn about it.
To associate your repository with the hmdb51 topic, visit your repo's landing page and select "manage topics."