AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models

zeyi shao, Haowen Hua, Jiaxin Zhang, John See, Zeyd Boukhers, Cong Yang

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 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 temporal-stable hard label rewriting (ablation)TecoPrompt · OxfordPets sym noise (avg)accuracy: 84.44 -> 86.26Improved
add temporal-stable rewriting (ablation)TecoPrompt · OxfordPets 70% sym noiseaccuracy: 78.22 -> 85.03Improved
add EMA confidence gate alone (no rewriting) (ablation)TecoPrompt · OxfordPets sym noise (avg)accuracy: 84.44 -> 84.67No clear effect
add EMA on top of rewriting (ablation)TecoPrompt · OxfordPets sym noise (avg)accuracy: 86.26 -> 86.96Mixed
use K=8 stability window instead of K=1 (ablation)TecoPrompt · OxfordPets sym noise (avg)accuracy: 80.59 -> 86.96Improved
use K=8 instead of K=16 (ablation)TecoPrompt · OxfordPets sym noise (avg)accuracy: 86.48 -> 86.96Improved
assign improper group-wise loss (0.7-0.5-0.3) (ablation)TecoPrompt · OxfordPets 70% sym noiseaccuracy: 85.36 -> 58.62Hurt
use temporally verified hard rewriting vs OT soft targets (ablation)TecoPrompt · Flowers102 80% asym noiseaccuracy: 71.80 -> 73.14Improved
TecoPrompt vs NLPrompt on real noisy labelsTecoPrompt · Food101Naccuracy: 76.46 -> 78.67Improved
TecoPrompt at low noise vs NLPromptTecoPrompt · DTD 12.5% sym noiseaccuracy: 63.0 vs 62.7No clear effect
temporal overhead of history and EMATecoPrompt · Caltech101 16-shottime per epoch: +0.20 seconds per epochNo clear effect

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