Retinomorphic Event-Driven Representations for Video Tasks

Simple item page
dc.contributor.advisorShrivastava, Anshumali
dc.contributor.committeeMemberPatel, Ankit B.
dc.creatorLiu, Wanjia
dc.date.accessioned2019-05-17T13:29:15Z
dc.date.available2019-05-17T13:29:15Z
dc.date.created2017-12
dc.date.issued2017-11-30
dc.date.submittedDecember 2017
dc.date.updated2019-05-17T13:29:15Z
dc.description.abstractDeep neural networks have revolutionized static image understanding through their amazing performance in tasks such as classification, segmentation and style transfer. However, current architectures have yet to find as much success in video tasks mainly due to increased data dimension, higher information throughput and a sub-optimal frame-driven representation. Inspired by the early vision systems of mammals and insects, we propose an event-driven input representation (EDR) that models several major properties of early retinal circuits: 1. Output scales logrithmically with input intensity, 2. ON/OFF pathways for differentiating event types, 3. Relative change detection and event detection via thresholding. With UCF-101 video action recognition experiments, we show that neural network utilizing EDR as input performs near state-of-the-art in accuracy while achieving a 1,500x speedup in input representation processing (9K frames/sec), as compared to optical flow. EDR's fast processing speed enables real-time inference/learning in time sensitive video applications such as reinforcement learning. In this vein, we use EDR to demonstrate performance improvements over state-of-the-art reinforcement learning algorithms for Atari games, something that has not been possible with optical flow.
dc.format.mimetypeapplication/pdf
dc.identifier.citationLiu, Wanjia. "Retinomorphic Event-Driven Representations for Video Tasks." (2017) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/105601">https://hdl.handle.net/1911/105601</a>.
dc.identifier.urihttps://hdl.handle.net/1911/105601
dc.language.isoeng
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.
dc.subjectRetinomorphic
dc.subjectEvent-Driven
dc.subjectMotion Representation
dc.subjectOptical-Flow
dc.subjectAction Recognition
dc.subjectReinforcement Learning
dc.titleRetinomorphic Event-Driven Representations for Video Tasks
dc.typeThesis
dc.type.materialText
thesis.degree.departmentComputer Science
thesis.degree.disciplineEngineering
thesis.degree.grantorRice University
thesis.degree.levelMasters
thesis.degree.majorDeep Learning
thesis.degree.nameMaster of Science
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
LIU-DOCUMENT-2017.pdf
Size:
3.55 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.6 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Electronic Theses and Dissertations