AI Paper Atlas

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

ImageBindDC: Compressing Multi-modal Data with ImageBind-based Condensation

Yue Min, Shaobo Wang, Jiaze Li, Tianle Niu, Junxin Fan, Yongliang Miao, Lijin Yang, Linfeng Zhang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 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 cross-modal and joint-modal alignment to uni-modal CF matching (ablation)ImageBindDC · AVE (10 DPC)accuracy: 70.34 -> 73.67Improved
replace MMD (DM) with characteristic function discrepancy (ablation)DM · AVE/VGGS uni-modal audio (1 DPC)accuracy: 27.87 -> 32.33Improved
replace MMD (DM) with characteristic function discrepancy (ablation)DM · Video-Audio (10 DPC)accuracy: 69.26 -> 70.34Improved
condense in ImageBind shared space with three CF objectives vs AVDDAVDD · VGGS-10K (10 DPC, ConvNet condensation)accuracy: 48.08 -> 55.23Improved
condense in ImageBind shared space with three CF objectives vs AVDDAVDD · AVE (1 DPC, ImageBind-guided)accuracy: 67.32 -> 70.10Improved
ImageBindDC vs AVDD on NYU-v2 at 10 DPCAVDD · NYU-v2 (10 DPC)accuracy: 98.62 -> 98.73No clear effect
ImageBindDC vs AVDD on NYU-v2 at 1 DPCAVDD · NYU-v2 (1 DPC)accuracy: 72.22 -> 80.43Improved
use ImageBindDC for condensation instead of DM/AVDDDM · VGGS-10K (1 DPC)condensation time (s): 140.30 -> 57.46Improved
ImageBindDC vs DM on ConvNet evaluation (AVE 1 DPC, ImageBind-guided condensation)DM · AVE ConvNet (1 DPC)accuracy: 7.10 -> 12.69Improved
ImageBindDC cross-architecture ConvNet at 10 DPCAVDD · AVE ConvNet (10 DPC)accuracy: 12.44 -> 16.74Mixed
ImageBindDC audio-text retrieval vs whole dataImageBindDC · Clotho (20 DPC)A2T R@10: 0.1995 vs 0.2364 wholeNo clear effect

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