Video Description using Bidirectional Recurrent Neural Networks
This work addresses video description generation for applications like accessibility and content indexing, but it is incremental as it builds on existing encoder-decoder frameworks.
The authors tackled the problem of generating video descriptions by enhancing an encoder-decoder model with richer image representations and bidirectional recurrent neural networks, resulting in more accurate descriptions that outperform previous state-of-the-art methods.
Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this work we propose pushing further this model by introducing two contributions into the encoding stage. First, producing richer image representations by combining object and location information from Convolutional Neural Networks and second, introducing Bidirectional Recurrent Neural Networks for capturing both forward and backward temporal relationships in the input frames.