AI Paper Atlas

Research map / Video / Video segmentation and tracking

Leaping Into Memories: Space-Time Deep Feature Synthesis

Alexandros Stergiou, Nikos Deligiannis

ICCV 2023 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 1 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 feature diversity and temporal coherence regularizers to model priming (ablation)LEAPS · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 67.9 -> 86.7Improved
add feature diversity regularizer to priming (ablation)LEAPS · Kinetics-400 val synthesized videos (X3D-M)top-1 accuracy of inverted model (%): 73.4 -> 81.1Improved
add temporal coherence regularizer to priming (ablation)LEAPS · Kinetics-400 val synthesized videos (X3D-M)top-1 accuracy of inverted model (%): 73.4 -> 78.0Improved
use priming from a stimulus video instead of plain DeepDream/AMvideo model inversion · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 41.4 -> 67.9Improved
use JVS instead of cosine as priming distance (ablation)LEAPS · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 72.1 -> 86.7Improved
use JVS instead of l2 priming distance (ablation)LEAPS · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 84.3 -> 86.7Improved
use priming loss on all layers instead of first 80% (ablation)LEAPS · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 69.3 -> 86.7Improved
increase synthesized video size from 8x224^2 to 16x224^2 (ablation)LEAPS · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 86.7 -> 87.0No clear effect
reduce spatial resolution of synthesized video to 8x182^2 (ablation)LEAPS · Kinetics-400 val synthesized videos (3D R50)top-1 accuracy of inverted model (%): 86.7 -> 84.3Hurt
apply temporal coherence regularization on all layers instead of final layer only (ablation)LEAPS · qualitative zumba examplevisual qualityHurt
use multiple stimuli instead of regularizersLEAPS · Kinetics-400 (3D R50, X3D-M)top-1 accuracyMixed

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