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

Taping Over Different Ground Profiles

Taping Over Different Ground Profiles

Taping over varying ground profiles requires careful adaptation to achieve accurate measurements. On smooth, level ground with minimal vegetation, the tape can rest directly on the ground. Here, the taping team, typically consisting of a head and a rear tapeman, coordinates their positions with clear communication. The rear tapeman holds the tape at the starting point and guides the head tapeman toward a range pole placed beyond the endpoint, using hand or voice signals to ensure alignment.On...

You might also read

Related Articles

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

Sort by

Same author

Chemistry-Informed Machine Learning Framework for Predicting Structural Properties in Osmabenzene Complexes.

The journal of physical chemistry letters·2026

Same author

Mask-Guided Self-Supervised Video Object Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Gut microbiota and bile acids profiles study of ulcerative colitis and Crohn's disease patients.

Frontiers in microbiology·2026

Same author

ChatLeafDisease: a chain-of-thought prompting approach for crop disease classification using large language models.

Plant phenomics (Washington, D.C.)·2025

Same author

SOX2 induces LPCAT1 expression to promote cholesterol metabolic reprogramming-mediated invasion and metastasis in osteosarcoma.

Frontiers in molecular biosciences·2025

Same author

Identification of routine blood derived hematological and lipid indices in ILD through machine learning; a retrospective case-control study.

Frontiers in medicine·2025

Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

Same journal

GoP-based Quality Enhancement on Video Compression.

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

Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 2, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

Zero-Shot Video Grounding With Pseudo Query Lookup and Verification.

Yu Lu, Ruijie Quan, Linchao Zhu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|February 19, 2024

Summary

This summary is machine-generated.

This study introduces a new zero-shot video grounding (ZS-VG) framework, Lookup-and-Verification (LoVe), to improve video understanding. LoVe efficiently identifies video moments using natural language queries without extensive manual annotation.

More Related Videos

Video-oculography in Mice

Video-oculography in Mice

Published on: July 19, 2012

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Related Experiment Videos

Last Updated: Jul 2, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

Video-oculography in Mice

Video-oculography in Mice

Published on: July 19, 2012

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Video grounding, identifying video segments from text queries, is crucial for video understanding.
Fully supervised methods require extensive data, hindering scalability.
Existing zero-shot video grounding (ZS-VG) methods struggle with diverse categories and contextual dynamics.

Purpose of the Study:

To address limitations in current ZS-VG approaches.
To develop a novel framework for efficient and accurate zero-shot video grounding.
To improve the recognition of diverse categories and contextual interactions in videos.

Main Methods:

Introduced a two-stage zero-shot video grounding (ZS-VG) framework named Lookup-and-Verification (LoVe).
Treated pseudo-query generation as a video-to-concept retrieval problem.
Implemented a verification process to ensure retrieved concepts align with video content.

Main Results:

The LoVe framework demonstrated effectiveness in zero-shot video grounding.
Achieved strong performance on benchmark datasets like Charades-STA, ActivityNet-Captions, and DiDeMo.
Showcased improved ability to recognize diverse categories and capture video dynamics.

Conclusions:

The LoVe framework offers a promising solution for zero-shot video grounding.
The proposed method enhances video understanding by overcoming limitations of existing approaches.
LoVe provides a scalable and effective approach for video moment retrieval.