01089nam a2200121Ia 4500008004100000041001200041082001600053100008200069245007300151260000900224510059400233650014000827231221s9999    xx            000 0 und d  aEnglish  aCPCS19-1854  aTanay Gangey. Hardik Gourisaria. Akhilarka Jayanthi. Rama Dev P. Shylaja S S. 0aGenerating Captions for Underwater Images Using Deep Learning Models  c2019  aImage captioning is a small yet important domain lying under the vast subject of Scene Understanding. Our work focusses on the generation of annotations for Underwater images in natural language. A new underwater image dataset, namely PESEmphasis5k, has been created and captioned. Our model using different variations of CNNs, LSTMs, and GRUs, when trained on our new dataset, generates captions with good accuracy. Alongside this, we introduce Parameter Wise Tally Checker as a new evaluation metrics for analyzing and evaluating models and demonstrate its usage on our captioning model.  aDeep Learning, Convolutional Neural Networks, Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Units, Image Captioning