AI Paper Atlas

Research map / Video / Action recognition

SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning

Ting Yao, Yiheng Zhang, Zhaofan Qiu, Yingwei Pan, Tao Mei

AAAI 2021 · Video › Action recognition · approach: Contrastive video representation learning · 100 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 intra-frame discrimination to inter-frame discrimination (ablation)SeCo · Kinetics400 validationTop-1: 58.97 -> 60.74Improved
Add intra-frame discrimination to inter-frame discrimination (ablation)SeCo · ActivityNet validationTop-1: 66.69 -> 68.31Improved
Add intra-frame discrimination to inter-frame discrimination (ablation)SeCo · OTB-100Precision: 67.92 -> 70.29Improved
Add temporal order validation to inter-frame and intra-frame discrimination (ablation)SeCo · Kinetics400 validationTop-1: 60.74 -> 61.91Improved
Add temporal order validation to inter-frame and intra-frame discrimination (ablation)SeCo · ActivityNet validationTop-1: 68.31 -> 68.55Improved
Add temporal order validation to inter-frame and intra-frame discrimination (ablation)SeCo · OTB-100Success: 50.48 -> 51.78Improved
Pre-train with SeCo instead of supervised ImageNet pre-trainingResNet50 fine-tuned with TSN · UCF101Top-1: 85.30 -> 88.26Improved
Pre-train with SeCo instead of supervised ImageNet pre-trainingResNet50 fine-tuned with TSN · HMDB51Top-1: 49.08 -> 55.55Improved
Use SeCo pre-training instead of VIE-FullResNet50 fine-tuned with TSN · UCF101Top-1: 80.40 -> 88.26Improved
Use SeCo pre-training instead of VIE-FullResNet50 fine-tuned with TSN · HMDB51Top-1: 52.50 -> 55.55Improved
Use SeCo (ResNet18) instead of VIE-FullKinetics400 representation learning · Kinetics400 validationTop-1: 48.53 -> 50.81Improved

Later papers that compared with this method

6 later accepted papers report SeCo as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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