AI Paper Atlas

Research map / Video / Video segmentation and tracking

Condensing a Sequence to One Informative Frame for Video Recognition

Zhaofan Qiu, Ting Yao, Yan Shu, Chong-Wah Ngo, Tao Mei

ICCV 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 9 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 adversarial regularizer to reconstruction-only IFS (end-to-end frames) (ablation)IFS app · Kinetics-400 valtop-1 accuracy: 71.7 -> 71.2Hurt
add adversarial regularizer to reconstruction-only IFS (JPEG frames) (ablation)IFS app · Kinetics-400 valtop-1 accuracy: 59.2 -> 70.3Improved
add color consistency regularizer on top of adversarial (ablation)IFS app+adv · Kinetics-400 valtop-1 accuracy: 71.2 -> 72.8Improved
add color consistency regularizer on top of adversarial (JPEG frames) (ablation)IFS app+adv · Kinetics-400 valtop-1 accuracy: 70.3 -> 72.8Improved
add motion estimation task to reconstruction (ablation)IFS app · Kinetics-400 valtop-1 accuracy: 72.8 -> 74.5Improved
add categorization task to reconstruction (ablation)IFS app · Kinetics-400 valtop-1 accuracy: 72.8 -> 73.7Improved
add categorization task to app+mot (full IFS) (ablation)IFS app+mot · Kinetics-400 valtop-1 accuracy: 74.5 -> 75.0Improved
add appearance reconstruction to cat+mot (ablation)IFS cat+mot · Kinetics-400 valtop-1 accuracy: 72.8 -> 75.0Improved
use reconstruction task instead of categorization task alone (ablation)IFS · Kinetics-400 valtop-1 accuracy: 68.2 -> 72.8Improved
add appearance reconstruction task to IFS-mot (ablation)IFS-mot · Kinetics-400 valtop-1 accuracy: 72.8 -> 75.0Improved
replace dynamic image pooling with learned IFS frameDI · Kinetics-400 valtop-1 accuracy: 71.6 -> 75.0Improved
fuse IFS frame with optical flow stream (ablation)IFS · Kinetics-400 valtop-1 accuracy: 75.0 -> 77.3Improved

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