AI Paper Atlas

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

Open-set Cross Modal Generalization via Multimodal Unified Representation

Hai Huang, Yan Xia, Shulei Wang, Hanting Wang, Minghui Fang, Shengpeng Ji, Sashuai Zhou, Tao Jin, Zhou Zhao

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 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
replace DCID with MICU on open-set cross-modal generalizationOSCMG · AVE, UCF, UCF(v)<->VGG(a)HOS: AVE Split1 V->A 51.54 -> 54.39Improved
use MICU on VGG(a)->UCF(v) Split2OSCMG · UCF(v)<->VGG(a) Split2 A->VHOS: 62.49 (DCID) -> 61.17Hurt
add L_fine to L_coarse (ablation)MICU · OSCMG AVE Split1 V->AHOS: 49.57 -> 54.05Improved
add L_cujp to L_coarse (ablation)MICU · OSCMG AVE Split1 V->AHOS: 49.57 -> 54.09Improved
use L_fine or L_cujp without L_coarse (ablation)MICU · OSCMG AVE Split1 V->AHOS: 9.17 (L_fine only), 11.46 (L_cujp only) vs 49.57 (L_coarse only)Hurt
use CUJP instead of MMJP jigsaw puzzles (ablation)MICU · OSCMG and CMG averagesOSCMG avg: 52.00 (MMJP6) -> 52.56 (CUJP4), 54.29 (CUJP8)Improved
use MMJP jigsaw instead of no jigsaw (ablation)MICU · OSCMG and CMG classificationperformanceHurt
increase CUJP splits from 4 to 8 (ablation)CUJP · OSCMG avgOSCMG average: 52.56 -> 54.29; memory 9.07GB -> 13.30GBImproved
use stronger backbones (Swin-V2-L, HTS-AT) (ablation)OSCMG methods · AVE Split1 V->AHOS: MICU 54.39 -> 57.76Improved
apply the same mask positions across paired modalities rather than different positions (ablation)FCMI · OSCMG/CMGperformanceImproved
use codebook size 400 instead of 256/512/800/1024 (ablation)MICU · OSCMG/CMGperformanceImproved

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