AI Paper Atlas

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

SAMPLE: Semantic Alignment through Temporal-Adaptive Multimodal Prompt Learning for Event-Based Open-Vocabulary Action Recognition

Jing Wang, Rui Zhao, Ruiqin Xiong, Xingtao Wang, Xiaopeng Fan, Tiejun Huang

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 3 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 Event-Text multimodal prompting to frozen CLIP (ablation)CLIP · SeActTop-1 accuracy: 9.85 -> 65.25Improved
add Temporal-Adaptive prompting to frozen CLIP (ablation)CLIP · SeActTop-1 accuracy: 9.85 -> 67.41Improved
add Temporal-Adaptive prompting on top of Event-Text prompting (ablation)SAMPLE · SeActTop-1 accuracy: 65.25 -> 69.79Improved
add Event-Text prompting on top of Temporal-Adaptive prompting (ablation)SAMPLE · SeActTop-1 accuracy: 67.41 -> 69.79Improved
add Temporal-Adaptive prompting on top of Event-Text prompting (ablation)SAMPLE · SeActTop-5 accuracy: 92.34 -> 97.83Improved
add Temporal-Adaptive prompting (extra parameters) on top of Event-Text prompting (ablation)SAMPLE · SeActtrainable parameters (M): 4.290 -> 8.681Mixed
vary prompt insertion depth J (ablation)SAMPLE · SeActTop-1 accuracy: zero-shot peaks at J = 8, fully-supervised at J = 12Mixed
prompt learning with frozen CLIP instead of fine-tuning the event encoder (SAMPLE vs ExACT)SAMPLE · zero-shot SeAct (trained on HARDVS)Top-1 accuracy: 11.54 -> 35.71Improved
prompt learning instead of ExACT fine-tuningSAMPLE · DVS128Gesture zero-shotTop-1 accuracy: 15.91 -> 55.17Improved
prompt learning instead of ExACT fine-tuningSAMPLE · base-to-novel HARDVS novel accuracynovel accuracy: 35.14 -> 63.22Improved
prompt learning instead of best prior method at 2 shotsSAMPLE · DVS128Gesture few-shot K=2Top-1 accuracy: 13.85 vs 18.92 (M2-CLIP)Hurt
prompt learning instead of best prior method at 2 shotsSAMPLE · SeAct few-shot K=2Top-1 accuracy: 20.34 -> 33.33Improved

Later papers that compared with this method

1 later accepted paper reports Sample 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