Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Diurnal rhythms of choice: a novel state-dependent drift diffusion model uncovers time-dependent changes in rat decision making.

bioRxiv : the preprint server for biology·2026
Same author

Leveraging insights from neuroscience to build adaptive artificial intelligence.

Nature neuroscience·2025
Same author

Advancing Mobile Neuroscience: A Novel Wearable Backpack for Multi-Sensor Research in Urban Environments.

Sensors (Basel, Switzerland)·2025
Same author

Joint modelling of brain and behaviour dynamics with artificial intelligence.

Nature reviews. Neuroscience·2025
Same author

Regulation of Decision Threshold by the Locus Coeruleus.

bioRxiv : the preprint server for biology·2025
Same author

Mice navigate scent trails using predictive policies.

bioRxiv : the preprint server for biology·2025
Same journal

Restraint of melanoma progression by cells in the local skin environment.

eLife·2026
Same journal

Brawn before bite in endemic Asian eutherian mammals after the end-Cretaceous extinction.

eLife·2026
Same journal

Experimental evolution to thermal stress indicates climate resilience in a cosmopolitan arthropod.

eLife·2026
Same journal

Correlates of protection against African swine fever virus identified by a systems immunology approach.

eLife·2026
Same journal

Retrosplenial cortex enables context-dependent goal-directed sensorimotor transformation.

eLife·2026
Same journal

Direct contact between iPSC-derived macrophages and hepatocytes drives reciprocal acquisition of Kupffer cell identity and hepatocyte maturation.

eLife·2026
See all related articles

Related Experiment Video

Updated: Nov 26, 2025

Movement Retraining using Real-time Feedback of Performance
08:16

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

13.6K

Real-time, low-latency closed-loop feedback using markerless posture tracking.

Gary A Kane1, Gonçalo Lopes2, Jonny L Saunders3

  • 1The Rowland Institute at Harvard, Harvard University, Cambridge, United States.

Elife
|December 8, 2020
PubMed
Summary
This summary is machine-generated.

DeepLabCut-Live! enables real-time animal pose estimation for neuroscience research. This low-latency tool offers zero-latency feedback and multiple integration options for seamless experimental control.

Keywords:
DeepLabCutany animalcomputational biologylow-latencymouseneurosciencepose-estimationreal-time trackingsystems biology

More Related Videos

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.5K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.7K

Related Experiment Videos

Last Updated: Nov 26, 2025

Movement Retraining using Real-time Feedback of Performance
08:16

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

13.6K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.5K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.7K

Area of Science:

  • Neuroscience
  • Computer Vision
  • Machine Learning

Background:

  • Real-time control of behavioral tasks and neural stimulation based on animal behavior is crucial for experimental neuroscientists.
  • Noninvasive, low-latency tools that interface with external hardware based on posture are highly desired.
  • Deep learning-based pose estimation has advanced the quantification of animal behaviors.

Purpose of the Study:

  • Introduce DeepLabCut-Live!, a novel package for real-time animal pose estimation.
  • Enhance experimental control by providing low-latency and zero-latency feedback mechanisms.
  • Facilitate the adoption of advanced pose estimation in neuroscience research.

Main Methods:

  • Developed DeepLabCut-Live! for low-latency (15 ms, >100 FPS) real-time pose estimation.
  • Integrated a forward-prediction module for zero-latency feedback.
  • Implemented a dynamic-cropping mode to increase inference speeds.
  • Provided a stand-alone GUI (DLC-Live! GUI) and integrations with Bonsai and AutoPilot.
  • Benchmarked performance across various systems to guide hardware selection.

Main Results:

  • Achieved real-time pose estimation with latency under 15 ms and frame rates exceeding 100 FPS.
  • Demonstrated zero-latency feedback capabilities through the forward-prediction module.
  • Showcased increased inference speeds using the dynamic-cropping mode.
  • Validated ease of use via the GUI and integrations with Bonsai and AutoPilot.

Conclusions:

  • DeepLabCut-Live! significantly advances real-time behavioral analysis for neuroscience.
  • The package offers flexible integration and high performance, lowering the barrier for advanced experimental control.
  • Provides essential benchmarks for researchers to select appropriate hardware for their needs.