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

Absolute Motion Analysis- General Plane Motion01:24

Absolute Motion Analysis- General Plane Motion

Visualize a drone, with its propellers spinning rapidly, hovering mid-air. The fascinating movements and operations of this drone can be comprehended by applying the principle of general plane motion.
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the drone...
Relative Motion Analysis using Rotating Axes01:25

Relative Motion Analysis using Rotating Axes

Consider a component AB undergoing a linear motion. Along with a linear motion, point B also rotates around point A. To comprehend this complex movement, position vectors for both points A and B are established using a stationary reference frame.
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it instrumental in...
Vector or Cross Product01:17

Vector or Cross Product

Vector multiplication of two vectors yields a vector product, with the magnitude equal to the product of the individual vectors multiplied by the sine of the angle between both the vectors and the direction perpendicular to both the individual vectors. As there are always two directions perpendicular to a given plane, one on each side, the direction of the vector product is governed by the right-hand thumb rule.
Consider the cross product of two vectors. Imagine rotating the first vector about...
Cross Product01:25

Cross Product

The cross product is a fundamental concept in vector algebra that is a vector operation on two different vectors to obtain a third vector. Unlike the scalar product, the cross product results in a vector quantity perpendicular to both the original vectors.
The magnitude of the cross product is obtained by multiplying the magnitude of both the vectors and the sine of the angle between them. This means that a larger angle between the vectors will lead to a greater magnitude of the cross product.
Cross Product and Its Geometry01:27

Cross Product and Its Geometry

In three-dimensional space, any two non-zero vectors that are not parallel define a unique plane and geometrically outline a parallelogram. The cross product of these vectors results in a third vector that is orthogonal to the plane formed by the initial two. This vector not only encodes information about direction but also reflects important physical quantities in applied contexts.The orientation of the cross product vector is determined using the Right-Hand Rule. When the fingers of the right...
Relative Motion Analysis using Rotating Axes-Problem Solving01:29

Relative Motion Analysis using Rotating Axes-Problem Solving

Consider a crane whose telescopic boom rotates with an angular velocity of 0.04 rad/s and angular acceleration of 0.02 rad/s2. Along with the rotation, the boom also extends linearly with a uniform speed of 5 m/s. The extension of the boom is measured at point D, which is measured with respect to the fixed point C on the other end of the boom. For the given instant, the distance between points C and D is 60 meters.
Here, in order to determine the magnitude of velocity and acceleration for point...

You might also read

Related Articles

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

Sort by
Same author

A multi-objective grey wolf optimization algorithm for energy-efficient cluster-based routing in IoT-enabled WSNs.

Scientific reports·2025
Same author

A hybrid vision transformer and ResNet18 based model for biotic rice leaf disease detection.

Frontiers in plant science·2025
Same author

A hybrid multi-layer perceptron with selective stacked ensemble learning approach for recognizing human activity using sensor dataset.

Scientific reports·2025
Same author

Health professionals' perspectives on the use of Artificial Intelligence in healthcare: A systematic review.

Patient education and counseling·2025
Same author

Diagnostic performance of artificial intelligence in detecting oral potentially malignant disorders and oral cancer using medical diagnostic imaging: a systematic review and meta-analysis.

Frontiers in oral health·2024
Same author

SWARAM: Osprey Optimization Algorithm-Based Energy-Efficient Cluster Head Selection for Wireless Sensor Network-Based Internet of Things.

Sensors (Basel, Switzerland)·2024

Related Experiment Videos

PoinCLIP-VAD: a hyperbolic cross-modal fusion framework for video anomaly detection.

Debi Prasad Senapati1, Santosh Kumar Pani1, Santos Kumar Baliarsingh2

  • 1School of Computer Engineering, KIIT Deemed to be University, Campus 25, Chandaka Industrial Estate Patia, Bhubaneswar, Odisha, 751024, India.

Scientific Reports
|June 8, 2026
PubMed
Summary

This study introduces PoinCLIP-VAD, a novel vision-language framework for weakly supervised video anomaly detection (WSVAD). By utilizing hyperbolic geometry, it enhances the detection of anomalies in videos with limited annotations.

Keywords:
Cross-modal interactionHyperbolic manifoldMultiple instance learningPoincaré distanceVideo anomaly detectionVision–language modelingWeakly supervised learning

Related Experiment Videos

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Weakly supervised video anomaly detection (WSVAD) faces challenges due to the lack of frame-level annotations, leading to noisy instance selection in Multiple Instance Learning (MIL).
  • Existing vision-language models, when using Euclidean space for feature representation, struggle with subtle semantic variations and ambiguous instance ranking in WSVAD.
  • The weak correspondence between video segments and semantic descriptions hinders effective anomaly detection.

Purpose of the Study:

  • To propose PoinCLIP-VAD, a vision-language framework that overcomes the limitations of Euclidean space by performing cross-modal fusion in hyperbolic space for improved WSVAD.
  • To enhance the representation of latent semantic relationships and improve similarity estimation between visual and textual features for anomaly detection.
  • To achieve more reliable anomaly discrimination and consistent cross-modal alignment under weak supervision.

Main Methods:

  • Embedding visual and textual features into a shared Poincaré ball geometry for non-linear distance scaling and expressive semantic representation.
  • Utilizing a dual-block architecture comprising a classification block for anomaly scoring and a video-text alignment block for fine-grained correspondence.
  • Employing negative Poincaré distance for robust similarity estimation and distinguishing normal from anomalous patterns.

Main Results:

  • PoinCLIP-VAD achieved an Area Under the Curve (AUC) of 90.62% on the UCF-Crime dataset.
  • The framework obtained an Average Precision (AP) of 86.93% on the XD-Violence dataset.
  • Demonstrated improved anomaly discrimination and more consistent cross-modal alignment in weakly supervised settings.

Conclusions:

  • PoinCLIP-VAD effectively leverages hyperbolic geometry for superior weakly supervised video anomaly detection.
  • The proposed framework offers a robust solution for handling noisy instance selection and weak semantic correspondence.
  • The results confirm the advantage of hyperbolic space in capturing subtle semantic variations for enhanced anomaly detection.