Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Purposive Learning

Purposive Learning

E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...

You might also read

Related Articles

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

Sort by

Same author

A prognostic model for head and neck squamous cell carcinoma based on eosinophil extracellular trap related genes.

Translational cancer research·2026

Same author

Nanomedicine-enabled in situ vaccination: Advancing a trilogy of immunogenic cell death induction, antigen presentation potentiation, and microenvironment remodeling.

Biomaterials·2026

Same author

Benchmarking Large Language Models for Bladder Cancer: Comparative Knowledge Retrieval and Clinical Reasoning of DeepSeek and ChatGPT.

Annals of surgical oncology·2026

Same author

CSVSUF: A Deep Unfolding Framework for Compressive Spectral Video Sensing.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Radiomics signatures based on computed tomography for noninvasive prediction of ICOS expression and prognosis in head and neck squamous cell carcinoma.

Medical physics·2026

Same author

Comparative outcomes of arthroscopy-assisted uniportal spinal surgery vs. unilateral biportal endoscopy for adjacent two-segment lumbar disc herniation: a retrospective cohort study.

Frontiers in surgery·2026

Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

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

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 6, 2025

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization.

Zhilin Li¹, Zilei Wang¹, Cerui Dong¹

¹National Engineering Laboratory for Brain-inspired Intelligence Technology and Application (NEL-BITA), University of Science and Technology of China, Hefei, 230026, China.

Neural Networks : the Official Journal of the International Neural Network Society

|November 24, 2024

Summary

This summary is machine-generated.

This study introduces the Multilevel Semantic and Adaptive Actionness Learning Network (SAL) for weakly supervised temporal action localization. SAL improves action classification and localization by learning fine-grained video semantics and using adaptive pseudo-labels.

Keywords:

Action recognition Temporal action localization Weakly supervised learning

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Related Experiment Videos

Last Updated: Jun 6, 2025

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Weakly supervised temporal action localization (WS-TAL) identifies actions in videos using only video-level labels.
Existing WS-TAL methods often use multiple instance learning with top-K segment selection, limiting fine-grained information capture.
This leads to suboptimal action classification and localization performance.

Purpose of the Study:

To propose a novel network, the Multilevel Semantic and Adaptive Actionness Learning Network (SAL), for improved WS-TAL.
To enhance the learning of fine-grained video semantics and actionness for better localization and classification.
To address the limitations of current WS-TAL methods in utilizing video information.

Main Methods:

The proposed SAL network comprises two branches: Multilevel Semantic Learning (MSL) and Adaptive Actionness Learning (AAL).
The MSL branch incorporates second-order video semantics to capture fine-grained details and improve classification, propagating these to action segments.
The AAL branch utilizes pseudo-labels with a video segments mix-up strategy and an adaptive actionness mask for stable training and improved generalization.

Main Results:

SAL achieves state-of-the-art performance on three benchmark datasets for weakly supervised temporal action localization.
The MSL branch effectively captures fine-grained video information, enhancing action classification.
The AAL branch improves the generalization ability and training stability through adaptive pseudo-labeling.

Conclusions:

The SAL network offers a significant advancement in weakly supervised temporal action localization.
The integration of multilevel semantics and adaptive actionness learning effectively addresses limitations in prior WS-TAL approaches.
SAL demonstrates superior performance, setting a new state-of-the-art on established benchmarks.