AI Paper Atlas

Research map / Video / Video-language understanding

Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline

Tiantian Geng, Teng Wang, Jinming Duan, Runmin Cong, Feng Zheng

CVPR 2023 · Video › Video-language understanding · approach: Dense video captioning · 34 citations (OpenAlex)

Read the paper

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
use audio and visual input together rather than visual input alone (ablation)Ours · UnAV-100 testaverage mAP: 35.9 -> 47.8Improved
use the proposed audio-visual model instead of ActionFormerUnAV-100 · UnAV-100 testaverage mAP: 42.2 -> 47.8Improved
add temporal downsampling across cross-modal pyramid levels (ablation)Cross-modal transformer · UnAV-100 testaverage mAP: 35.3 -> 39.4Improved
increase cross-modal pyramid levels from two to six with temporal downsampling (ablation)Cross-modal transformer · UnAV-100 testaverage mAP: 39.4 -> 47.8Improved
increase cross-modal pyramid levels from six to seven (ablation)Cross-modal transformer · UnAV-100 testaverage mAP: 47.8 -> 46.8Hurt
add two uni-modal transformer blocks before cross-modal interaction (ablation)Cross-modal transformer · UnAV-100 testaverage mAP: 46.7 -> 47.8Improved
add temporal dependency modeling (ablation)Dense-localization model · UnAV-100 testaverage mAP: 45.2 -> 46.1Improved
add class-aware regression (ablation)Dense-localization model · UnAV-100 testaverage mAP: 45.2 -> 45.8Improved
use dependency modeling and class-aware regression together (ablation)Dense-localization model · UnAV-100 testaverage mAP: 45.2 -> 47.8Improved
use I3D RGB and optical-flow features instead of RGB-only I3D features (ablation)Visual feature extractor · UnAV-100 testaverage mAP: 46.7 -> 47.8Improved
add position embeddings (ablation)Transformer encoder · UnAV-100 testaverage mAP: 47.0 -> 47.8Improved
increase temporal feature stride from 8 to 16 (ablation)Audio-visual feature extraction · UnAV-100 testaverage mAP: 47.8 -> 46.7Hurt

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