AI Paper Atlas

Research map / Video / Action recognition

TempCLR: Temporal Alignment Representation with Contrastive Learning

Yuncong Yang, Jiawei Ma, Shiyuan Huang, Long Chen, Xudong Lin, Guangxing Han, Shih-Fu Chang

ICLR 2023 · Video › Action recognition · approach: Contrastive video representation learning · 0 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 sequence-level contrastive temporal alignment during zero-shot trainingVideoCLIP · CrossTask zero-shot action step localizationrecall: 33.9 to 36.9Improved
use TempCLR pretraining for few-shot recognitionSomething-Something V2 · 1-shot action recognitionaccuracy: 45.4 to 47.8Improved
use TempCLR pretraining for few-shot recognitionSomething-Something V2 · 5-shot action recognitionaccuracy: 64.6 to 67.7Improved
add temporal-alignment learningVideoCLIP · DiDeMo clip-caption retrievalR@1: 16.6 to 17.7Improved
shuffle clip order within each segment in addition to segment order (ablation)TempCLR seg-only negatives · CrossTask supervised action step localizationrecall: 52.1 to 52.5Improved
replace seg-unit negatives with within-segment shuffling only (ablation)TempCLR · CrossTask supervised action step localizationrecall: 52.5 to 46.4Hurt
replace seg-unit negatives with unpaired-video negatives (ablation)TempCLR · CrossTask supervised action step localizationrecall: 52.5 to 48.0Hurt
replace seg-unit negatives with all-unit shuffling (ablation)TempCLR · CrossTask supervised action step localizationrecall: 52.5 to 49.3Hurt
add unpaired-video negatives to seg-unit negatives (ablation)TempCLR · CrossTask supervised action step localizationrecall: 52.5 to 52.5No clear effect
update all parameters instead of norm layers only during zero-shot pretraining (ablation)TempCLR · CrossTask zero-shot action step localization with OTAMrecall: 36.1 to 36.9Improved
use DTW instead of OTAM for zero-shot evaluation (ablation)TempCLR + All Params. · CrossTask zero-shot action step localizationrecall: 36.9 to 36.9No clear effect
use DTW instead of OTAM for full-video retrieval (ablation)TempCLR · full-video retrieval, background keptR@1: 72.2 to 70.4Hurt

Later papers that compared with this method

1 later accepted paper reports TempCLR as a baseline in their results tables; 1 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