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

Stereotypes, Prejudice, and Discrimination02:55

Stereotypes, Prejudice, and Discrimination

95.0K
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who...
95.0K
Crossed Aldol Reaction Using Weak Bases01:14

Crossed Aldol Reaction Using Weak Bases

2.7K
This lesson deals with the crossed aldol reaction using weak bases. The self-condensation of an aldehyde having α hydrogen is prevented by adding it slowly to a mixture of formaldehyde and weak bases like hydroxide and alkoxide. Upon slow addition of the aldehyde, the base deprotonates the α carbon of the aldehyde to form the corresponding enolate. The enolate subsequently attacks the formaldehyde to form a single crossed product. Figure 1 depicts the aforementioned reaction.
2.7K
Local Anesthetics: Mechanism of Action01:23

Local Anesthetics: Mechanism of Action

3.3K
Local anesthetics (LAs) block sensory and motor impulses by inhibiting the sodium channels on the nerve cell membranes. This induces temporary loss of sensation, relieving pain in a specific body area.
Local anesthetics are amphiphilic molecules consisting of a hydrophobic aromatic part linked to a hydrophilic group by an ester or amide linkage. They are weak bases and are usually available as salts, which increases their solubility and stability. Once administered, LAs exist in the body either...
3.3K
Weak Base Solutions03:21

Weak Base Solutions

24.9K
Some compounds produce hydroxide ions when dissolved by chemically reacting with water molecules. In all cases, these compounds react only partially and so are classified as weak bases. These types of compounds are also abundant in nature and important commodities in various technologies. For example, global production of the weak base ammonia is typically well over 100 metric tons annually, being widely used as an agricultural fertilizer, a raw material for chemical synthesis of other...
24.9K
Weak Acid Solutions04:02

Weak Acid Solutions

42.4K
Few compounds act as strong acids. A far greater number of compounds behave as weak acids and only partially react with water, leaving a large majority of dissolved molecules in their original form and generating a relatively small amount of hydronium ions. Weak acids are commonly encountered in nature, being the substances partly responsible for the tangy taste of citrus fruits, the stinging sensation of insect bites, and the unpleasant smells associated with body odor. A familiar example of a...
42.4K
Titration of a Weak Acid with a Weak Base01:08

Titration of a Weak Acid with a Weak Base

4.9K
Weak acids and bases do not undergo dissociation completely, and titrations between these two are rarely studied. When such studies are performed, say, for the titration of a weak acid with a weak base, the titration curve plots the change in pH as a function of the volume of base added. Take the titration of acetic acid with ammonia, for instance. During the titration, these two species form ammonium acetate and water, but the pH change is slow and gradual.
As a result, there is no simple...
4.9K

You might also read

Related Articles

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

Sort by
Same author

Identification of genes controlling grain size in barley through RNA-seq and weighted gene co-expression network analysis.

Functional & integrative genomics·2026
Same author

Spatiotemporal Context-Aware Prompting With Low-Rank Dynamic Routing for Exemplar-Free Video Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026
Same author

Transcription factor HvDREB4.1 and HvDREB4.2 from Hulless barley enhance tolerance to drought and salt stress in transgenic Arabidopsis thaliana.

BMC plant biology·2026
Same author

Mapping barley leaf stripe resistence in Tibetan hulless barley based on BSR-seq and Iso-seq.

BMC genomics·2026
Same author

Correction: Effect of hulless barley flours on dough rheological properties, Baking Quality, and Starch Digestibility of Wheat Bread.

Frontiers in nutrition·2026
Same author

Adaptive and lightweight surrogate gradients: enhancing training efficiency of spiking neural networks.

Frontiers in neuroscience·2026

Related Experiment Video

Updated: Jan 27, 2026

Measurement & Analysis of the Temporal Discrimination Threshold Applied to Cervical Dystonia
10:05

Measurement & Analysis of the Temporal Discrimination Threshold Applied to Cervical Dystonia

Published on: January 27, 2018

10.2K

Cross-category spatiotemporal consensus and discriminative networks for weakly-supervised temporal action

Kunlun Wu1, Donghai Zhai1

  • 1School of Computing and Artificial Intelligence, Southwest Jiaotong University, No.999 Xian Avenue, Chengdu, 611756, Sichuan China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 25, 2026
PubMed
Summary

This study introduces the STCD network for weakly-supervised temporal action localization, improving accuracy by considering cross-category similarities and higher-order dynamics for better video analysis.

Keywords:
Discriminative features enhancementHigher-order dynamicsSuperclass-level semanticsWeakly-supervised temporal action localization

More Related Videos

Inducible LAP-tagged Stable Cell Lines for Investigating Protein Function, Spatiotemporal Localization and Protein Interaction Networks
11:04

Inducible LAP-tagged Stable Cell Lines for Investigating Protein Function, Spatiotemporal Localization and Protein Interaction Networks

Published on: December 24, 2016

10.2K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.5K

Related Experiment Videos

Last Updated: Jan 27, 2026

Measurement & Analysis of the Temporal Discrimination Threshold Applied to Cervical Dystonia
10:05

Measurement & Analysis of the Temporal Discrimination Threshold Applied to Cervical Dystonia

Published on: January 27, 2018

10.2K
Inducible LAP-tagged Stable Cell Lines for Investigating Protein Function, Spatiotemporal Localization and Protein Interaction Networks
11:04

Inducible LAP-tagged Stable Cell Lines for Investigating Protein Function, Spatiotemporal Localization and Protein Interaction Networks

Published on: December 24, 2016

10.2K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.5K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Weakly-supervised temporal action localization (WS-TAL) aims to identify action instances in untrimmed videos without frame-level annotations.
  • Existing WS-TAL methods often focus on enhancing action snippet features or exploring non-salient regions, but neglect cross-category consensus and higher-order dynamics.
  • These overlooked aspects, cross-category consensus relationships and class-level higher-order dynamics, offer crucial information for comprehensive localization and capturing subtle discriminative features.

Purpose of the Study:

  • To develop a novel method, the STCD network, for improved weakly-supervised temporal action localization.
  • To leverage superclass-level semantics and high-order dynamics for spatiotemporal consensus and discriminative learning.
  • To enhance the discriminative features of action snippets by reducing uncertainty and minimizing information entropy.

Main Methods:

  • The STCD network utilizes a high-order encoding module based on Koopman theory to explore discriminative class-wise dynamics.
  • Superclass-level semantics are employed to capture consensus relationships among actions with similar sub-actions.
  • An information-theoretic loss function is proposed to reduce the uncertainty of ambiguous action snippets by minimizing their information entropy.

Main Results:

  • The proposed STCD network demonstrates superior performance compared to state-of-the-art methods on benchmark datasets.
  • Experimental results on THUMOS14, ActivityNet v1.2, and ActivityNet v1.3 validate the effectiveness of the approach.
  • The method successfully leverages cross-category consensus and higher-order dynamics for more comprehensive action localization.

Conclusions:

  • The STCD network offers a simple yet effective approach for weakly-supervised temporal action localization.
  • Incorporating superclass semantics and high-order dynamics significantly enhances localization accuracy.
  • The information-theoretic loss function effectively improves the discriminative power of action features.