Imagine This! Scripts to Compositions to Videos

by   Tanmay Gupta, et al.

Imagining a scene described in natural language with realistic layout and appearance of entities is the ultimate test of spatial, visual, and semantic world knowledge. Towards this goal, we present the Composition, Retrieval, and Fusion Network (CRAFT), a model capable of learning this knowledge from video-caption data and applying it while generating videos from novel captions. CRAFT explicitly predicts a temporal-layout of mentioned entities (characters and objects), retrieves spatio-temporal entity segments from a video database and fuses them to generate scene videos. Our contributions include sequential training of components of CRAFT while jointly modeling layout and appearances, and losses that encourage learning compositional representations for retrieval. We evaluate CRAFT on semantic fidelity to caption, composition consistency, and visual quality. CRAFT outperforms direct pixel generation approaches and generalizes well to unseen captions and to unseen video databases with no text annotations. We demonstrate CRAFT on FLINTSTONES, a new richly annotated video-caption dataset with over 25000 videos. For a glimpse of videos generated by CRAFT, see


page 1

page 10

page 14

page 19

page 21

page 22


On Semantic Similarity in Video Retrieval

Current video retrieval efforts all found their evaluation on an instanc...

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

Current methods for learning visually grounded language from videos ofte...

Where to Play: Retrieval of Video Segments using Natural-Language Queries

In this paper, we propose a new approach for retrieval of video segments...

Spatio-Temporal Scene Graphs for Video Dialog

The Audio-Visual Scene-aware Dialog (AVSD) task requires an agent to ind...

Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval

Schemata are structured representations of complex tasks that can aid ar...

Representing Videos based on Scene Layouts for Recognizing Agent-in-Place Actions

We address the recognition of agent-in-place actions, which are associat...

Temporally Coherent Bayesian Models for Entity Discovery in Videos by Tracklet Clustering

A video can be represented as a sequence of tracklets, each spanning 10-...

Code Repositories


repo for interesting AI related topics and references

view repo