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

Upsampling01:22

Upsampling

565
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
565
Downsampling01:20

Downsampling

570
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
570
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

1.0K
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
1.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

14.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.5K
3.5K

You might also read

Related Articles

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

Sort by
Same author

Deciphering Core Geometry for the Rational Design of Copper(I) Iodide Cluster Scintillators Toward Computed Tomography Imaging.

Angewandte Chemie (International ed. in English)·2026
Same author

Interstitial Nitrogen Tuning of Magnetocrystalline Anisotropy and High-Frequency Electromagnetic Properties in Nd-Based 3:29-Type Intermetallics.

Journal of the American Chemical Society·2026
Same author

Selective Laser Trabeculoplasty Mitigates Dexamethasone-Induced Myofibroblast-Like Transformation and Dysfunction in Human Trabecular Meshwork Cells.

Current eye research·2026
Same author

Photoinduced Structural Relaxation in Chiral Copper(l) Iodide Cluster Scintillators for Circularly Polarized Radioluminescence Imaging.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Structure based identification of novel 4,5,6,7-tetrahydro-7H-pyrazolo[3,4-c]pyridin-7-one derivatives as nonacidic ATX inhibitors with promising antifibrotic effects.

European journal of medicinal chemistry·2026
Same author

Morphology Control of Ag<sub>2</sub>S and Heterojunction Engineering in Ag<sub>2</sub>S/Bi<sub>2</sub>S<sub>3</sub>/WO<sub>3</sub> Films for Boosting Photoreduction of Cr(VI).

Langmuir : the ACS journal of surfaces and colloids·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Jan 7, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

721

SAM-I2V++: Efficiently Upgrading SAM for Promptable Video Segmentation.

Haiyang Mei, Pengyu Zhang, Mike Zheng Shou

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 26, 2025
    PubMed
    Summary
    This summary is machine-generated.

    SAM-I2V++ efficiently upgrades image segmentation models for videos, achieving high performance with minimal training cost. This method enables precise, temporally consistent mask propagation in dynamic scenes for promptable video segmentation (PVS).

    More Related Videos

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    25.0K
    AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells
    06:03

    AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

    Published on: June 23, 2023

    791

    Related Experiment Videos

    Last Updated: Jan 7, 2026

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    721
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    25.0K
    AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells
    06:03

    AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

    Published on: June 23, 2023

    791

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Foundation models like Segment Anything Model (SAM) excel at promptable image segmentation.
    • Extending SAM to video segmentation faces challenges in temporal consistency and dynamic scene handling.
    • Training large video segmentation models like SAM 2 incurs significant computational costs.

    Purpose of the Study:

    • To develop a training-efficient method for promptable video segmentation (PVS) by upgrading existing image segmentation models.
    • To reduce the computational complexity and resource requirements for PVS model development.
    • To enable precise and temporally consistent mask propagation in dynamic video scenes.

    Main Methods:

    • Introduced SAM-I2V++, an image-to-video upgradation method for promptable video segmentation (PVS).
    • Developed an image-to-video feature extraction upgrader leveraging SAM's static encoder for spatiotemporal perception.
    • Implemented a memory selective associator with multiscale-enhanced cross-attention for frame association.
    • Utilized a memory-as-prompt mechanism with object memory for consistent mask propagation.

    Main Results:

    • SAM-I2V++ achieves 93% of SAM 2's performance.
    • The method requires only 0.2% of SAM 2's training cost.
    • Demonstrated effective mask propagation in dynamic scenes.

    Conclusions:

    • SAM-I2V++ offers a resource-efficient pathway to promptable video segmentation.
    • The approach significantly lowers barriers for PVS research and deployment.
    • Enables broader applications and advancements in video analysis.