Generating Captions: Describing Videos with Neural Networks

It´s clearly not magic. My experiments point this out playfully. Blackboxes don´t help innovation and education. In terms of research, lots of exiting work happening across the board, worth tracking and learning.

At the moment it is much more interesting when applied to more narrowly targeted tasks. These can include video captioning but for clearly specified tasks. The (too quick of a) tentative jump from well automated targeted tasks to generic task automation is the culprit here.

In my few years of practice of deep neural networks in industry, I can say they are very nice to work with as they fit a large number of tasks and yield excellent results for many of them.

I don't think many serious deep learning researchers claim that it will solve any kind of problems. Instead, it allows us to make significant strides in areas that have been stagnant for many years now (e.g., image recognition, speech recognition, some natural language tasks, and other domain-specific tasks). The potential impact based on these "narrow" domains is already huge (voice commands, image search, analyze medical images, analyze legal/medical documents, aid self-driving cars, etc.). Basically, it allows us to turn data that is highly structured but in a complex way (e.g., images, voice) into standard classification/regression problems. So far, I don't think it does much more than that.