AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning

Xin Wang, Jiawei Wu, Da Zhang, Yu Su, William Yang Wang

AAAI 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 36 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
Compose topic-conditioned primitive experts instead of using the Base captionerActivityNet-Captions zero-shot video captioning · ActivityNet-Captions unseen test setCIDEr: 22.51 -> 28.23Improved
Add topic-conditioned expert composition to the Base modelActivityNet-Captions captioning · ActivityNet-Captions seen test setCIDEr: 31.48 -> 35.53Improved
Add pretrained fasttext embeddings instead of task-specific embeddingsTAMoE · ActivityNet-Captions unseen test setCIDEr: 24.39 -> 28.23Improved
Add the topic embedding to the Base modelActivityNet-Captions zero-shot video captioning · ActivityNet-Captions unseen test setCIDEr: 22.51 -> 24.06Improved
Add the average activity-label embedding to I3D video features (ablation)TAMoE · ActivityNet-Captions unseen test setCIDEr: 22.51 -> 25.96Improved
Add the external-corpus TFIDF embedding to I3D video features (ablation)TAMoE · ActivityNet-Captions unseen test setCIDEr: 22.51 -> 26.61Improved
Combine average label and TFIDF embeddings with I3D video features (ablation)TAMoE · ActivityNet-Captions unseen test setCIDEr: 22.51 -> 28.23Improved
Remove I3D video features (ablation)TAMoE · ActivityNet-Captions unseen test setCIDEr: 28.23 -> 15.77Hurt
Use a single expert instead of a multi-expert mixture (ablation)TAMoE · ActivityNet-Captions validation setCIDErHurt
Increase the expert count to 256 with expert dimension 128 rather than using 8 experts of dimension 256 (ablation)TAMoE · ActivityNet-Captions validation setCIDErHurt
Use topic-aware mixture-of-experts captioning rather than BaseMSR-VTT · MSR-VTTCIDEr: 47.2 -> 48.9Improved
Use TAMoE rather than Base for individual novel activitiesActivityNet-Captions · Novel activitiesCIDErMixed

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