AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

i-Code: An Integrative and Composable Multimodal Learning Framework

Ziyi Yang, Yuwei Fang, Chenguang Zhu, Reid Pryzant, DongDong Chen, Yu Shi, Yichong Xu, Yao Qian, Mei Gao, Yi-Ling Chen, Liyang Lu, Yujia Xie and 8 more

AAAI 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

Read the paper

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
Pretrain on dual-modality datasets instead of no pretraining (ablation)i-Code Merge · CMU-MOSEI SentimentMAE: 0.529 -> 0.502Improved
Pretrain on dual-modality datasets instead of no pretraining (ablation)i-Code Merge · CMU-MOSEI Emotion RecognitionAccuracy: 49.2 -> 49.4Improved
Use video pretraining rather than dual-dataset pretraining (ablation)i-Code Merge · UR-FUNNYAccuracy: 76.94 -> 79.17Improved
Use dual-dataset pretraining rather than video pretraining (ablation)i-Code Merge · CMU-MOSEI SentimentMAE: 0.519 -> 0.502Improved
Combine dual-dataset and video pretraining (ablation)i-Code Merge · CMU-MOSEI Emotion RecognitionAccuracy: 49.4 -> 49.8Improved
Replace merge-attention with co-attention (ablation)i-Code with dual-data pretraining · CMU-MOSEI SentimentMAE: 0.502 -> 0.525Hurt
Replace merge-attention with co-attention (ablation)i-Code with dual-data pretraining · CMU-MOSEI Emotion RecognitionAccuracy: 49.4 -> 50.2Improved
Add language to speech-only input (ablation)i-Code · CMU-MOSEI Emotion RecognitionAccuracy: 47.3 -> 49.2Improved
Add vision, language, and speech rather than language and speech only (ablation)i-Code · CMU-MOSEI Emotion RecognitionAccuracy: 49.2 -> 49.4Improved
Replace WavLM-large with HuBERT-large (ablation)i-Code Dual+Merge · VIOLINAccuracy: 72.9 -> 72.1Hurt
Use learnable rather than fixed loss-combination weights (ablation)i-Code pretraining · downstream tasksperformanceNo clear effect
Use the pretrained multimodal fusion framework rather than no fusion pretraining (ablation)i-Code · How2QA public testAccuracy: 74.41 -> 75.41Improved

Later papers that compared with this method

1 later accepted paper reports i-Code 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