Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning
This work addresses the problem of enhancing creative freedom and user engagement in vision+language modeling for applications like automated captioning, though it is incremental as it builds on existing latent variable models.
The paper tackled the challenge of achieving fine-grained control over diverse image captioning by proposing Seq-CVAE, which learns a latent space for each word position to capture sentence intention, resulting in significant improvements in diversity metrics on the MSCOCO dataset while maintaining sentence quality.
Diverse and accurate vision+language modeling is an important goal to retain creative freedom and maintain user engagement. However, adequately capturing the intricacies of diversity in language models is challenging. Recent works commonly resort to latent variable models augmented with more or less supervision from object detectors or part-of-speech tags. Common to all those methods is the fact that the latent variable either only initializes the sentence generation process or is identical across the steps of generation. Both methods offer no fine-grained control. To address this concern, we propose Seq-CVAE which learns a latent space for every word position. We encourage this temporal latent space to capture the 'intention' about how to complete the sentence by mimicking a representation which summarizes the future. We illustrate the efficacy of the proposed approach to anticipate the sentence continuation on the challenging MSCOCO dataset, significantly improving diversity metrics compared to baselines while performing on par w.r.t sentence quality.