AI Paper Atlas

Research map / Video / Video segmentation and tracking

Enhancing Self-Supervised Video Representation Learning via Multi-Level Feature Optimization

Rui Qian, Yuxi Li, Huabin Liu, John See, Shuangrui Ding, Xian Liu, Dian Li, Weiyao Lin

ICCV 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 36 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 combined instance+semantic graph targets for lower-level features (multi-level) (ablation)R3D-18 baseline · UCF-101 linear probetop-1 accuracy: 58.1 -> 63.2Improved
add combined graph targets for lower-level features (multi-level) (ablation)R3D-18 baseline · HMDB-51 linear probetop-1 accuracy: 28.8 -> 33.4Improved
use one-hot labels for lower-level features (ablation)R3D-18 baseline · UCF-101 linear probetop-1 accuracy: 58.1 -> 57.8Hurt
use instance-wise distribution only for lower-level features (ablation)R3D-18 baseline · UCF-101 linear probetop-1 accuracy: 58.1 -> 59.4Improved
use semantic-wise distribution only for lower-level features (ablation)R3D-18 baseline · UCF-101 linear probetop-1 accuracy: 58.1 -> 54.5Hurt
apply combined graph constraint to lower-level features rather than only high-level (ablation)R3D-18 · UCF-101 linear probetop-1 accuracy: 60.4 -> 63.2Improved
add own temporal modeling (NTM) vs none (ablation)R3D-18 · UCF-101 linear probetop-1 accuracy: 55.9 -> 63.2Improved
add own temporal modeling (NTM) vs none (ablation)S3D · UCF-101 linear probetop-1 accuracy: 53.8 -> 61.1Improved
add own temporal modeling (NTM) vs none (ablation)SlowFast · UCF-101 linear probetop-1 accuracy: 57.8 -> 63.9Improved
use conventional input-level temporal augmentation instead of none (ablation)R3D-18 · UCF-101 linear probetop-1 accuracy: 55.9 -> 43.2Hurt
use conventional input-level temporal augmentation instead of none (ablation)S3D · UCF-101 linear probetop-1 accuracy: 53.8 -> 41.1Hurt
use conventional input-level temporal augmentation instead of none (ablation)SlowFast · UCF-101 linear probetop-1 accuracy: 57.8 -> 65.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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