AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatial-temporal Causal Inference for Partial Image-to-video Adaptation

Jin Chen, Xinxiao Wu, Yao Hu, Jiebo Luo

AAAI 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 16 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
Use the spatial-temporal causal framework with causality-guided mappings and class-wise alignmentpartial image-to-video adaptation · S→Uclassification accuracy (%): 84.63 -> 95.15Improved
Use the spatial-temporal causal framework with causality-guided mappings and class-wise alignmentpartial image-to-video adaptation · E→Hclassification accuracy (%): 32.80 -> 52.66Improved
Add effects inferred by causal inference (ablation)image-to-video adaptation · S→Uclassification accuracy (%): 90.74 -> 95.15Improved
Add effects inferred by causal inference (ablation)image-to-video adaptation · E→Hclassification accuracy (%): 43.79 -> 52.66Improved
Add the spatial domain shift effect (ablation)image-to-video adaptation · S→Uclassification accuracy (%): 91.92 -> 95.15Improved
Add the spatial domain shift effect (ablation)image-to-video adaptation · E→Hclassification accuracy (%): 48.40 -> 52.66Improved
Add the temporal domain shift effect (ablation)image-to-video adaptation · S→Uclassification accuracy (%): 93.85 -> 95.15Improved
Add the temporal domain shift effect (ablation)image-to-video adaptation · E→Hclassification accuracy (%): 45.33 -> 52.66Improved
Add the video-to-image mapping (ablation)bidirectional heterogeneous image-video mappings · S→Uclassification accuracy (%): 43.13 -> 95.15Improved
Add the video-to-image mapping (ablation)bidirectional heterogeneous image-video mappings · E→Hclassification accuracy (%): 38.05 -> 52.66Improved
Add cycle consistency loss (ablation)bidirectional heterogeneous image-video mappings · S→Uclassification accuracy (%): 34.80 -> 95.15Improved
Add cycle consistency loss (ablation)bidirectional heterogeneous image-video mappings · E→Hclassification accuracy (%): 32.96 -> 52.66Improved

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