AnnikaLindh

Annika Lindh AnnikaLindh

PhD student in AI, Deep Learning, Computer Vision and NLG. My current focus is multi-modal learning with visual and NLG components.

Achievements

Diverse_and_Specific_Image_Captioning Diverse_and_Specific_Image_Captioning Public

Unsupervised specificity-guided optimization of Image Captioning models to encourage meaningful diversity in the generated captions. Code for the paper Generating Diverse and Meaningful Captions: U…

Python 13 8
DBNTensorFlow DBNTensorFlow Public

TensorFlow implementations of a Restricted Boltzmann Machine and an unsupervised Deep Belief Network, including unsupervised fine-tuning of the Deep Belief Network.

Python 3 1
Controllable_Region_Pointer_Advancement Controllable_Region_Pointer_Advancement Public

PyTorch implementation of a Controllable Image Captioning model with a language-driven mechanism for advancing the region pointer state that keeps it in sync with the state of the language model. C…

Python 2 1
show-prefer-tell show-prefer-tell Public

Pipeline model for controllable image captioning with user preference settings. Code and model output for the paper Show, Prefer and Tell: Incorporating User Preferences into Image Captioning (Lind…

Python
tool_caffe2pytorch tool_caffe2pytorch Public

Helper tool to allow PyTorch to load Caffe weights in the format used by the Faster R-CNN in the Bottom-Up network for image captioning.

Python