Adversarial Inference for Multi-Sentence Video Description
This work addresses video description challenges for AI applications, but it is incremental as it adapts adversarial techniques from image captioning to video inference.
The paper tackles the problem of generating fluent, coherent, and relevant multi-sentence descriptions for long videos by proposing an adversarial inference method with a multi-discriminator design that evaluates visual relevance, language diversity, and coherence. It demonstrates improved accuracy, diversity, and coherence on the ActivityNet Captions dataset through automatic and human evaluations.
While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among the main issues are the fluency and coherence of the generated descriptions, and their relevance to the video. Recently, reinforcement and adversarial learning based methods have been explored to improve the image captioning models; however, both types of methods suffer from a number of issues, e.g. poor readability and high redundancy for RL and stability issues for GANs. In this work, we instead propose to apply adversarial techniques during inference, designing a discriminator which encourages better multi-sentence video description. In addition, we find that a multi-discriminator "hybrid" design, where each discriminator targets one aspect of a description, leads to the best results. Specifically, we decouple the discriminator to evaluate on three criteria: 1) visual relevance to the video, 2) language diversity and fluency, and 3) coherence across sentences. Our approach results in more accurate, diverse, and coherent multi-sentence video descriptions, as shown by automatic as well as human evaluation on the popular ActivityNet Captions dataset.