AI Paper Atlas

Research map / Video / Video-language understanding

TACo: Token-Aware Cascade Contrastive Learning for Video-Text Alignment

Jianwei Yang, Yonatan Bisk, Jianfeng Gao

ICCV 2021 · Video › Video-language understanding · approach: Video-language pretraining · 123 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 token-level loss L2 (noun+verb) on top of L1+L3 with cascade (ablation)TACo · YouCook2 R@1R@1: 15.0 -> 15.8Improved
add token-level loss L2 (noun+verb) on top of L1+L3 with cascade (ablation)TACo · MSR-VTT split1 R@1R@1: 23.7 -> 24.5Improved
add cascade hard negative sampling to L1+L3 (ablation)TACo · YouCook2 R@1R@1: 13.9 -> 15.0Improved
add cascade hard negative sampling to L1+L3 (ablation)TACo · MSR-VTT split1 R@1R@1: 22.5 -> 23.7Improved
combine early-stage L1 with later-stage L3 instead of L3 only (ablation)TACo · YouCook2 R@1R@1: 13.3 -> 13.9Improved
token loss on determiners and adpositions instead of none (ablation)TACo · YouCook2 R@1R@1: 15.0 -> 14.7Hurt
token loss on nouns only instead of none (ablation)TACo · YouCook2 R@1R@1: 15.0 -> 15.4Improved
token loss on verbs only instead of none (ablation)TACo · YouCook2 R@1R@1: 15.0 -> 15.3Improved
use nouns+verbs instead of nouns only as tokens of interest (ablation)TACo · YouCook2 R@1R@1: 15.4 -> 15.8Improved
add video encoder layers (0 to 4) (ablation)TACo · YouCook2 R@1 (R-152+S3D-HM)R@1: 14.0 -> 16.4Improved
use cascade sampling on later-stage alignment instead of early+later stage losses only (ablation)TACo · YouCook2 later-stage R@1R@1: 13.6 -> 14.5Improved
use TACo losses instead of baseline lossTACo · YouCook2 R@1 (R-152+S3D-HM)R@1: 13.3 -> 15.8Improved

Later papers that compared with this method

7 later accepted papers report TACO as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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