rm-rf-me / simple-action-recognition
基于cnn的视频动作分类教程。
☆11Updated 4 years ago
Related projects: ⓘ
- ☆48Updated 6 years ago
- ST-GCN-5-25☆9Updated 5 years ago
- 中文领域的多模态Bert☆46Updated 4 years ago
- 用yoloV3进行人的侦测，再用SPPE（Alphapose）进行骨架提取，再用连续30帧的ST-GCN进行行为识别。站立、走路、跌倒行为识别，在https://github.com/GajuuzZ/Human-Falling-Detect-Tracks的./models里…☆58Updated 3 years ago
- ☆159Updated this week
- 图像中文描述☆94Updated 6 years ago
- Image Caption workout with NIC and NBT☆15Updated 5 years ago
- Pytorch impelementation for Temporal Segment Networks (TSN) in ECCV 2016☆42Updated 5 years ago
- Detect the face in each key frame which extracts from the movie☆25Updated 3 years ago
- ☆44Updated 2 years ago
- This project includes the whole training process.☆16Updated 3 years ago
- 500,000 multimodal short video data and baseline models. 50万条多模态短视频数据集和基线模型（TensorFlow2.0）。☆127Updated 5 years ago
- Frames Extraction With OpenCV and Python☆15Updated 4 years ago
- ST-GCN-5-25☆27Updated 5 years ago
- 动作识别(Action Recognition)常见模型的Pytorch实现☆25Updated 3 years ago
- 视频的文本摘要(标注)，输入一段视频，通过深度学习网络和人工智能程序识别视频主要表达的意思(Input a video output a txt decribing the video)。☆179Updated 6 years ago
- PyTorch implementation of Chinese image captioning on AI_challenger dataset☆34Updated 4 years ago
- Run Online-Realtime-Action-Recognition-based-on-OpenPose sucess☆11Updated 3 years ago
- 图像中文描述+视觉注意力☆182Updated 4 years ago
- This is a Pytorch implement of StNet:Local and Global Spatial-Temporal Modeling for Action Recognition.☆8Updated 5 years ago
- 2021腾讯广告算法大赛赛道二神奈川冲浪里(获奖排名第8)☆15Updated 2 years ago
- Action recognition based on OpenPose and 2s-AGCN☆10Updated 4 years ago
- Cross-lingual image captioning☆82Updated 2 years ago
- 2021 腾讯广告赛算法大赛 赛道二 决赛第六名☆35Updated last year
- The implementation for "Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition" (ECCV2020).☆101Updated 3 years ago
- 中文CLIP：自定义数据集，可根据文图提取向量，实现文图匹配。☆21Updated 2 years ago
- 基于lightopenpose的跌倒、运动动作训练与识别☆35Updated 2 years ago
- PyTorch implementation of Graph-Based Social Relation Reasoning (ECCV 2020)☆16Updated 8 months ago
- Using VideoBERT to tackle video prediction☆116Updated 3 years ago
- 这是一个基于Pytorch平台、Transformer框架实现的视频描述生成 (Video Captioning) 深度学习模型。 视频描述生成任务指的是：输入一个视频，输出一句描述整个视频内容的文字（前提是视频较短且可以用一句话来描述）。本repo主要目的是帮助视力障碍…☆78Updated 2 years ago