Abstract: Methods and systems for generating video previews are provided. In one embodiment, a method includes acquiring a video. The method allows extracting features of the video. The method further includes determining, based on the features, a genre of the video. The method can proceed with selecting, based on the features and the genre, a time fragment of the video. The method further includes cropping the time fragment to a rectangular shape to fit a screen of a mobile device positioned vertically. The method further includes compressing the cropped fragment into low bitrate video fragment.

Abstract: Provided are methods and system for recognizing characters such as mathematical expressions or chemical formulas. An example method comprises the steps of receiving and processing an image by a pre-processing module to obtain one or more candidate regions, extracting features of each of the candidate regions by a feature extracting module such as a convolutional neural network (CNN), encoding the features into a distributive representation for each of the candidate regions separately using an encoding module such as a first long short-term memory (LSTM) based neural network, decoding the distributive representation into output representations using a decoding module such as a second LSTM-based recurrent neural network, and combining the output representations into an output expression, which is outputted in a computer-readable format or a markup language.

Abstract: Provided are methods and system for recognizing characters such as mathematical expressions or chemical formulas. An example method comprises the steps of receiving and processing an image by a pre-processing module to obtain one or more candidate regions, extracting features of each of the candidate regions by a feature extracting module such as a convolutional neural network (CNN), encoding the features into a distributive representation for each of the candidate regions separately using an encoding module such as a first long short-term memory (LSTM) based neural network, decoding the distributive representation into output representations using a decoding module such as a second LSTM-based recurrent neural network, and combining the output representations into an output expression, which is outputted in a computer-readable format or a markup language.