AI Paper Atlas

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

Watch, Listen and Tell: Multi-Modal Weakly Supervised Dense Event Captioning

Tanzila Rahman, Bicheng Xu, Leonid Sigal

ICCV 2019 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 99 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 MFCC audio features to C3D video features (MUTAN fusion)unimodal C3D captioner · ActivityNet Captions final modelBLEU@4: 0.83 -> 0.90Improved
add MFCC audio features to C3D video features (MUTAN fusion)unimodal C3D captioner · ActivityNet Captions final modelmIoU: 29.78 -> 30.02Improved
add MFCC audio features to C3D video featuresunimodal C3D captioner · ActivityNet Captions final modelCIDEr: 13.81 -> 13.79No clear effect
add SoundNet audio features to C3D video featuresunimodal C3D captioner · ActivityNet Captions final modelMETEOR: 4.89 -> 5.03Improved
add MFCC audio to video featuresunimodal C3D captioner · ActivityNet Captions (ground-truth segments)CIDEr: 24.46 -> 25.36Improved
add SoundNet audio to video featuresunimodal C3D captioner · ActivityNet Captions (ground-truth segments)CIDEr: 24.46 -> 24.22Hurt
use audio only instead of video onlyunimodal captioner · ActivityNet Captions final modelCIDEr: 13.81 -> 9.56Hurt
use MUTAN fusion instead of multiplicative mixture fusion (ablation)MFCC + C3D multi-modal model · ActivityNet Captions final modelmIoU: 29.87 -> 30.02Improved
use MUTAN fusion instead of multi-modal context fusion (ablation)MFCC + C3D multi-modal model · ActivityNet Captions pretrained modelCIDEr: 7.91 -> 8.20Improved
use MUTAN fusion instead of multiplicative mixture fusion (ablation)MFCC + C3D multi-modal model · ActivityNet Captions final modelCIDEr: 13.97 -> 13.79Hurt
use MFCC audio instead of CQT audioaudio-only captioner · ActivityNet Captions final modelCIDEr: 8.97 -> 9.56Improved
add multi-modal MFCC audio with zero vectors for missing audiopretrained captioner · ActivityNet Captions full datasetCIDEr: 10.45 -> 10.53Improved

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