Show, Tell and Rephrase: Diverse Video Captioning via Two-Stage Progressive Training

Describing a video using natural language is an inherently one-to-many translation task. To generate diverse captions, existing VAE-based generative models typically learn factorized latent codes via one-stage training merely from stand-alone video-caption pairs. However, such a paradigm neglects set-level relationships among captions from the same video, not fully capturing the underlying multimodality of the generative process. To overcome this shortcoming, we leverage neighbouring descriptions for the same video that are articulated with noticeable topics and language variations (i.e., paraphrases). To this end, we propose a novel progressive training method by decomposing the learning of latent variables into two stages that are topic-oriented and paraphrase-oriented, respectively. Specifically, the model learns from divergent topic sentences obtained by semantic-based clustering in the first stage. It is then trained again through paraphrases with a cluster-aware adaptive regularization, allowing more intra-cluster variations. Furthermore, we introduce an overall metric DAUM, a
D
iversity-
A
ccuracy
U
nified
M
etric to consider both the precision of the generated caption set and its coverage on the reference set, which has proved to have a higher correlation with human judgment than previous precision-only metrics. Extensive experiments on three large-scale video datasets show that the proposed training strategy can achieve superior performance in terms of accuracy, diversity, and DAUM over several baselines.