Dense Optical Flow Prediction from a Static Image
- 1 December 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2015 IEEE International Conference on Computer Vision (ICCV)
- p. 2443-2451
- https://doi.org/10.1109/iccv.2015.281
Abstract
Given a scene, what is going to move, and in what direction will it move? Such a question could be considered a non-semantic form of action prediction. In this work, we present a convolutional neural network (CNN) based approach for motion prediction. Given a static image, this CNN predicts the future motion of each and every pixel in the image in terms of optical flow. Our CNN model leverages the data in tens of thousands of realistic videos to train our model. Our method relies on absolutely no human labeling and is able to predict motion based on the context of the scene. Because our CNN model makes no assumptions about the underlying scene, it can predict future optical flow on a diverse set of scenarios. We outperform all previous approaches by large margins.Keywords
Other Versions
This publication has 16 references indexed in Scilit:
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- PANDA: Pose Aligned Networks for Deep Attribute ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Predicting Object Dynamics in ScenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Max-Margin Early Event DetectorsInternational Journal of Computer Vision, 2013
- DeepFlow: Large Displacement Optical Flow with Deep MatchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Anticipating Human Activities using Object Affordances for Reactive Robotic ResponsePublished by Robotics: Science and Systems Foundation ,2013
- HMDB: A large video database for human motion recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- A Data-Driven Approach for Event PredictionLecture Notes in Computer Science, 2010
- Long Short-Term MemoryNeural Computation, 1997