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

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

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

Sort by

Same author

Blood host preferences and competitive inter-species dynamics within an African malaria vector species complex inferred from signs of animal activity around aquatic larval habitats.

PloS one·2026

Same author

Utilization Patterns and Optimization Suggestions for Wildlife Passages in Xinjiang Nature Reserves.

Ecology and evolution·2025

Same author

Land Use Change Consistently Reduces α- But Not β- and γ-Diversity of Bees.

Global change biology·2025

Same author

A Broadband Photodetector Based on PbS Quantum Dots and Graphene with High Responsivity and Detectivity.

Nanomaterials (Basel, Switzerland)·2023

Same author

Evaluation of the Protection Effectiveness of Natural Protected Areas on the Qinghai-Tibet Plateau Based on Ecosystem Services.

International journal of environmental research and public health·2023

Same author

Estimating Carbon Sequestration Potential of Forest and Its Influencing Factors at Fine Spatial-Scales: A Case Study of Lushan City in Southern China.

International journal of environmental research and public health·2022

Search research articles

Related Experiment Video

Updated: May 18, 2026

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Published on: June 2, 2014

AviaTAD-LGH: A Multi-Task Spatio-Temporal Action Detector with Lightweight Gradient Harmonization for Real-Time Avian

Zihui Xie^1,2, Haifang Jian², Wenhui Yang³

¹School of Communication and Electronic Engineering, Shandong Normal University, Jinan 250358, China.

Sensors (Basel, Switzerland)

|April 14, 2026

Summary

This summary is machine-generated.

Researchers developed AviaTAD-LGH, a new framework for fine-grained spatio-temporal action detection in videos. This approach improves accuracy in complex environments, aiding ecological monitoring.

Keywords:

deep learning ecological monitoring multi-task learning spatio-temporal action detection video sensing

More Related Videos

A Video Surveillance System to Monitor Breeding Colonies of Common Terns Sterna Hirundo

A Video Surveillance System to Monitor Breeding Colonies of Common Terns Sterna Hirundo

Published on: July 22, 2018

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Related Experiment Videos

Last Updated: May 18, 2026

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Published on: June 2, 2014

A Video Surveillance System to Monitor Breeding Colonies of Common Terns Sterna Hirundo

A Video Surveillance System to Monitor Breeding Colonies of Common Terns Sterna Hirundo

Published on: July 22, 2018

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Area of Science:

Computer Vision
Artificial Intelligence
Ecological Monitoring

Background:

Fine-grained spatio-temporal action detection is challenging due to background clutter and similar actions.
Existing benchmarks lack sufficient domain-specific data for complex behaviors.

Purpose of the Study:

Introduce a large-scale benchmark for wintering crane behavior analysis.
Propose a novel real-time multi-task framework (AviaTAD-LGH) for enhanced action detection.

Main Methods:

Developed the Wintering-Crane Benchmark with dense, individual-level annotations.
Proposed AviaTAD-LGH, a dual-pathway 3D backbone with auxiliary motion supervision.
Introduced Lightweight Gradient Harmonization (LGH) to mitigate negative transfer in multi-task learning.

Main Results:

Achieved state-of-the-art mean Average Precision (mAP) of 68.60%.
Outperformed strong public baselines by 7.44% and single-task baseline by 2.80%.
Demonstrated significant improvements on ambiguous dynamic action classes.

Conclusions:

AviaTAD-LGH offers efficient and scalable solutions for ecological monitoring.
The proposed methods enable real-time, accurate action detection suitable for edge deployment.