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 Experiment Videos

Robust object recognition with cortex-like mechanisms.

Thomas Serre1, Lior Wolf, Stanley Bileschi

  • 1Massachusetts Institute of Technology, Center for Biological and Computational Learning, McGovern Institute for Brain Research and Brain & Cognitive Sciences Department, MA 02139, USA. serre@mit.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 17, 2007
PubMed
Summary
This summary is machine-generated.

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

Extensive Experience Remodels Neural Task Circuitry to Escape the Frontal Bottleneck and Increase Automaticity of Categorization.

Journal of cognitive neuroscience·2026
Same author

Distinct cross-modal coupling between the written and auditory language networks during reading and spoken word processing.

Brain and language·2026
Same author

Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Non-invasive quantification of viability in liver spheroids using deep learning.

Frontiers in bioengineering and biotechnology·2026
Same author

Towards noninvasive blood count using a deep learning pipeline from bulbar conjunctiva videos.

NPJ digital medicine·2026
Same author

Perilesional neuromodulation replaces lost sensorimotor function in persons with spinal cord injury.

Nature biomedical engineering·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

We developed a novel biologically-inspired framework for complex visual scene recognition. This hierarchical system achieves high performance on diverse tasks, learning efficiently from limited data.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Current computer vision systems struggle with complex scene recognition.
  • Biological systems offer sophisticated models for visual processing.

Purpose of the Study:

  • To introduce a novel, biologically-constrained framework for complex visual scene recognition.
  • To evaluate the framework's performance on various recognition tasks.

Main Methods:

  • A hierarchical system mimicking the visual cortex.
  • Alternating template matching and maximum pooling for feature representation.
  • Demonstration on object recognition, categorization, and scene understanding tasks.

Main Results:

Related Experiment Videos

  • The framework successfully performs invariant single object recognition, multiclass categorization, and complex scene understanding.
  • Achieves state-of-the-art performance despite biological constraints.
  • Demonstrates effective learning from few training examples.

Conclusions:

  • The proposed framework offers a powerful and biologically plausible approach to visual scene recognition.
  • Suggests a universal, redundant feature dictionary for object recognition.
  • Provides evidence for feedforward models in cortical object recognition.