AI Paper Atlas

Research map / Video / Video-language understanding

UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization

Tiantian Geng, Teng Wang, Jinming Duan, Yanfu Zhang, Weili Guan, Feng Zheng, Ling Shao

TPAMI 2025 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 17 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 task-specific experts and language-aware classifier to naive multi-task modelnaive multi-task model · All three tasksall-tasks average mAP: 47.7 -> 48.9Improved
train all tasks jointly with the unified model instead of single-task modelsUniAV · DESED (SED)average mAP: 57.7 -> 59.8Improved
fine-tune single-task models from the all-task modelUniAV AT · All three tasksall-tasks average mAP: 48.9 -> 49.7Improved
naive multi-task training instead of single-tasksingle-task models · ActivityNet 1.3 (TAL)average mAP: 35.3 -> 34.8Hurt
cross-task transfer of TAL model to AVEL (head fine-tuning only)single-task TAL model · UnAV-100 (AVEL)average mAP: 49.6 -> 29.8Hurt
jointly train SED with AVELUniAV · DESED (SED)average mAP: 57.7 -> 59.4Improved
jointly train SED with AVELUniAV · UnAV-100 (AVEL)average mAP: 49.6 -> 48.3Hurt
replace separate classifiers with language-aware classification head (ablation)UniAV · DESED (SED)average mAP: 54.8 -> 59.7Improved
add task-specific experts to later blocks rather than early blocks (ablation)UniAV · UnAV-100 (AVEL)average mAP: 50.5 -> 50.8Improved
add task-specific experts instead of widening dimension to 768 (ablation)UniAV w/o experts · ActivityNet 1.3 (TAL)average mAP: 34.9 -> 36.1Improved
add audio to visual input for TAL (ablation)ST TAL model · ActivityNet 1.3 (TAL)average mAP: 34.2 -> 35.3Improved
add visual to audio input for SED (ablation)ST SED model · DESED (SED)average mAP: 49.5 -> 57.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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