Blocksworld Revisited: Learning and Reasoning to Generate Event-Sequences from Image Pairs

by   Tejas Gokhale, et al.

The process of identifying changes or transformations in a scene along with the ability of reasoning about their causes and effects, is a key aspect of intelligence. In this work we go beyond recent advances in computational perception, and introduce a more challenging task, Image-based Event-Sequencing (IES). In IES, the task is to predict a sequence of actions required to rearrange objects from the configuration in an input source image to the one in the target image. IES also requires systems to possess inductive generalizability. Motivated from evidence in cognitive development, we compile the first IES dataset, the Blocksworld Image Reasoning Dataset (BIRD) which contains images of wooden blocks in different configurations, and the sequence of moves to rearrange one configuration to the other. We first explore the use of existing deep learning architectures and show that these end-to-end methods under-perform in inferring temporal event-sequences and fail at inductive generalization. We then propose a modular two-step approach: Visual Perception followed by Event-Sequencing, and demonstrate improved performance by combining learning and reasoning. Finally, by showing an extension of our approach on natural images, we seek to pave the way for future research on event sequencing for real world scenes.


page 1

page 2

page 3

page 4


HySTER: A Hybrid Spatio-Temporal Event Reasoner

The task of Video Question Answering (VideoQA) consists in answering nat...

End-to-End Learned Event- and Image-based Visual Odometry

Visual Odometry (VO) is crucial for autonomous robotic navigation, espec...

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

Spatial-temporal reasoning is a challenging task in Artificial Intellige...

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Recent work in computer vision and cognitive reasoning has given rise to...

Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images

Event recognition in still images is an intriguing problem and has poten...

Visual Reasoning: from State to Transformation

Most existing visual reasoning tasks, such as CLEVR in VQA, ignore an im...

Solving Visual Analogies Using Neural Algorithmic Reasoning

We consider a class of visual analogical reasoning problems that involve...

Please sign up or login with your details

Forgot password? Click here to reset