AI Paper Atlas

Research map / Video / Video segmentation and tracking

Temporal Transductive Inference for Few-Shot Video Object Segmentation

Mennatullah Siam

IJCV 2025 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add global video-level loss (ablation)RePRI baseline · YouTube-VIS FS-VOSmVC3: 66.3 -> 67.3Improved
add keyframe refinement (ablation)TTI with global loss · YouTube-VIS FS-VOSmVC3: 67.3 -> 70.6Improved
add dense contrastive learning (ablation)TTI with global loss and keyframe refinement · YouTube-VIS FS-VOSmVC3: 70.6 -> 72.1Improved
add dense contrastive learning (ablation)TTI with global loss and keyframe refinement · YouTube-VIS FS-VOS fold 1mVC3: 59.6 -> 57.7Hurt
learn per-frame classifiers with temporal regularization instead of single set of weights over all frames (ablation)Naive Temporal RePRI · YouTube-VIS FS-VOSmIoU: 51.0 -> 60.5Improved
add temporal transductive inference to RePRIRePRI · YouTube-VIS FS-VOSmIoU: 59.5 -> 60.5Improved
add temporal transductive inference to RePRIRePRI · YouTube-VIS FS-VOSmVC3: 66.3 -> 72.1Improved
add temporal transductive inference to RePRIRePRI · YouTube-VIS FS-VOS fold 4mIoU: 64.2 -> 62.4Hurt
add temporal transductive inference to RePRIRePRI · MiniVSPWmIoU: 27.1 -> 29.3Improved
add temporal transductive inference to RePRIRePRI · MiniVSPWmVC3: 22.9 -> 26.9Improved
add temporal transductive inference to RePRIRePRI · YouTube-VIS FS-VOSboundary accuracy F: 43.5 -> 45.0Mixed
operate on final linear classifiers instead of fine-tuning backbone onlineTTI vs DANet · YouTube-VIS FS-VOSruntime per video: 20 s -> 3 sImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy