AI Paper Atlas

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

Connecting Multi-modal Contrastive Representations

Zehan Wang, Yang Zhao, Xize Cheng, Haifeng Huang, Jiageng Liu, Aoxiong Yin, Li Tang, Linjun Li, Yongqi Wang, Ziang Zhang, Zhou Zhao

NeurIPS 2023 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning

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
connect CLIP and CLAP via overlapping text, without paired audio-visual training dataAudio-visual representations · AVE and Flickr-SoundNet retrievalmAP: 4.11, 4.13, 4.57, 4.92Improved
connect CLIP and ULIP-2 through images3D-language representations · ModelNet40Top1: 74.0 -> 64.9Mixed
add text-text inter-MCR alignment (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 3.28 -> 4.11Improved
add pseudo audio-visual inter-MCR alignment (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 4.09 -> 4.11No clear effect
add both inter-MCR alignment losses (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 0.22 -> 4.11Improved
add intra-CLIP and intra-CLAP alignment (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 3.14 -> 4.11Improved
add Gaussian noise and re-normalization to embeddings (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 2.77 -> 4.11Improved
add re-normalization after noise (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 3.70 -> 4.11Improved
use softmax memory aggregation instead of argmax selection (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 4.01 -> 4.11Improved
use semantic memory selection rather than random memory selection (ablation)C-MCR audio-visual retrieval · AVE A2ImAP: 2.62 -> 4.11Improved
vary the Gaussian noise variance (ablation)C-MCR audio-visual retrieval · AVE and Flickr-SoundNetaverage mAPNo 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