pith. machine review for the scientific record. sign in

arxiv: 1704.07489 · v2 · submitted 2017-04-24 · 💻 cs.CL · cs.AI· cs.CV

Recognition: unknown

Multi-Task Video Captioning with Video and Entailment Generation

Authors on Pith no claims yet
classification 💻 cs.CL cs.AIcs.CV
keywords videotaskcaptioningentailmentgenerationimprovementsmulti-tasklearn
0
0 comments X
read the original abstract

Video captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics involved in the task still remains a challenge, especially given the lack of sufficient annotated data. We improve video captioning by sharing knowledge with two related directed-generation tasks: a temporally-directed unsupervised video prediction task to learn richer context-aware video encoder representations, and a logically-directed language entailment generation task to learn better video-entailed caption decoder representations. For this, we present a many-to-many multi-task learning model that shares parameters across the encoders and decoders of the three tasks. We achieve significant improvements and the new state-of-the-art on several standard video captioning datasets using diverse automatic and human evaluations. We also show mutual multi-task improvements on the entailment generation task.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.