AI Paper Atlas

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

Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities

Jindi Bao, Jianjun Qian, Mengkai Yan, Jian Yang

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 1 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 Progressive Interaction module (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 71.32 -> 77.11Improved
add Adaptive Modality Reliability Estimator (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 74.96 -> 77.11Improved
add confidence-based modality importance (CMI) (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 76.12 -> 77.11Improved
add Fisher information-based modality importance (FIMI) (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 76.09 -> 77.11Improved
add feature uniformity loss (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 75.73 -> 77.11Improved
add phase consistency loss (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 76.63 -> 77.11Improved
add Progressive Interaction module (ablation)PRLF · CMU-MOSI (full modality {l,a,v})F1: 79.33 -> 85.78Improved
increase iteration step from 1 to 4 (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 72.29 -> 77.11Improved
increase iteration step from 4 to 5 (ablation)PRLF · CMU-MOSI (inter-modality missing)F1: 77.11 -> 75.80Hurt
increase iteration step from 1 to 4 (ablation)PRLF · CMU-MOSI (intra-modality missing, p=0.9)F1: 55.37 -> 58.64Improved
increase iteration step from 4 to 5 (ablation)PRLF · CMU-MOSI (intra-modality missing, p=0.9)F1: 58.64 -> 57.48Hurt
PRLF vs HRLFPRLF · CMU-MOSI (inter-modality missing)F1: 76.74 -> 77.02Improved

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