chenxinpeng / S2VT
Tensorflow implement of paper: Sequence to Sequence: Video to Text
☆88Updated 6 years ago
Alternatives and similar repositories for S2VT:
Users that are interested in S2VT are comparing it to the libraries listed below
- Soft attention mechanism for video caption generation☆156Updated 7 years ago
- Using Semantic Compositional Networks for Video Captioning☆96Updated 6 years ago
- Sentence/Caption evaluation using automated metrics☆60Updated 8 years ago
- Code for "Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner" in ICCV 2017☆148Updated 6 years ago
- Tensorflow implement of paper: Optimization of image description metrics using policy gradient methods☆29Updated 6 years ago
- Caffe☆206Updated 7 years ago
- Contains approaches introduced in the MovieQA benchmark dataset paper☆79Updated 8 years ago
- Supplementary material to "Top-down Visual Saliency Guided by Captions" (CVPR 2017)☆107Updated 7 years ago
- ☆50Updated 8 years ago
- automatic video description generation with GPU training☆258Updated 5 years ago
- Tensorflow Implementation of Deeper LSTM+ normalized CNN for Visual Question Answering☆100Updated 7 years ago
- Using scene-specific contexts and region-based attention in neural image captioning☆43Updated 4 years ago
- PyTorch Implementation of Consensus-based Sequence Training for Video Captioning☆59Updated 6 years ago
- Co-attending Regions and Detections for VQA.☆40Updated 6 years ago
- Code for paper "Image Caption Generation with Text-Conditional Semantic Attention"☆60Updated 7 years ago
- 🎬 Video Captioning: ICCV '15 paper implementation☆47Updated 6 years ago
- This repo allocate DAPs code of our ECCV 2016 publication☆77Updated 6 years ago
- ActionVLAD for video action classification (CVPR 2017)☆215Updated 6 years ago
- tensorflow implementation of show, attend and tell (ICML'15)☆19Updated 7 years ago
- Activity Recognition in Videos using UCF101 dataset☆60Updated 10 years ago
- SST: Single-Stream Temporal Action Proposal☆67Updated 7 years ago
- Temporal augmentation with two-stream ConvNet features on human action recognition☆18Updated 7 years ago
- Implementation for our paper "Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues."☆39Updated 7 years ago
- Attention Bidirectional Video Recurrent Net☆56Updated 5 years ago
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos☆69Updated 7 years ago
- The Theano code for the CVPR 2017 paper "Semantic Compositional Networks for Visual Captioning"☆69Updated 6 years ago
- A video captioning tool using S2VT method and attention mechanism (TensorFlow)☆15Updated 6 years ago
- Code for detecting visual concepts in images.☆150Updated 6 years ago
- Caffe implementation of paper: "Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering"☆29Updated 6 years ago
- Action Recognition Toolbox for CUHKÐZ&SIAT submission to ActivityNet 2016☆251Updated 6 years ago