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

Detecting objects of variable shape structure with hidden state shape models.

Jingbin Wang1, Vassilis Athitsos, Stan Sclaroff

  • 1Google Inc, Mountain View, CA 94043, USA. jingbinw@cs.bu.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 16, 2008
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

FIT: Enhancing multimodal knowledge graph completion via fine-grained interaction and TriConvTransformer.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia.

Machine learning in clinical neuroimaging : 7th international workshop, MLCN 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 10, 2024, proceedings. MLCN (Workshop) (7th : 2024 : Marrakesh, Morocco)·2026
Same author

Global research trends in signaling pathways of spasmolytic polypeptide-expressing metaplasia pathogenesis: a bibliometric analysis.

Frontiers in oncology·2026
Same author

FourierMIL: Fourier Filtering-based Multiple Instance Learning for Whole Slide Image Analysis.

International journal of computer vision·2025
Same author

Cellular lineage origins of spasmolytic polypeptide-expressing metaplasia (SPEM): persistent and intensifying debates.

Frontiers in oncology·2025
Same author

A predictive nomogram for peritoneal injury during totally extraperitoneal inguinal hernia repair: A retrospective cohort study.

The Journal of international medical research·2025
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

This study introduces Hidden State Shape Models (HSSMs) for accurate object detection in cluttered images. The novel method excels at identifying objects with variable shapes, outperforming existing techniques.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Object detection in cluttered images is challenging due to variations in object appearance.
  • Existing methods struggle with objects exhibiting complex and variable shape structures.

Purpose of the Study:

  • To propose a robust method for detecting object classes with variable shape structures.
  • To introduce Hidden State Shape Models (HSSMs) as a probabilistic framework for this task.

Main Methods:

  • Developed Hidden State Shape Models (HSSMs), a generalization of Hidden Markov Models (HMMs).
  • Employed a polynomial inference algorithm for automatic object localization, orientation, scale, and structure determination.
  • Integrated temporal constraints for enhanced performance and speed.

Related Experiment Videos

Main Results:

  • Achieved high accuracy in localizing objects with variable shape structures in real-world cluttered images.
  • Demonstrated superior performance compared to chamfer-distance matching for hand shape localization.
  • Obtained significant speed-ups (over an order of magnitude) and accurate results in non-rigid hand motion tracking.

Conclusions:

  • HSSMs provide an effective probabilistic framework for modeling and detecting objects with variable shape structures.
  • The proposed method offers significant improvements in accuracy and efficiency over existing techniques.
  • The approach is well-suited for applications like non-rigid object tracking in dynamic environments.