XGC-AVis: Towards Audio-Visual Content Understanding with a Multi-Agent Collaborative System
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916974177550336 |
|---|---|
| author | Cao, Yuqin Min, Xiongkuo Gao, Yixuan Sun, Wei Zhang, Zicheng Han, Jinliang Zhai, Guangtao |
| author_facet | Cao, Yuqin Min, Xiongkuo Gao, Yixuan Sun, Wei Zhang, Zicheng Han, Jinliang Zhai, Guangtao |
| contents | In this paper, we propose XGC-AVis, a multi-agent framework that enhances the audio-video temporal alignment capabilities of multimodal large models (MLLMs) and improves the efficiency of retrieving key video segments through 4 stages: perception, planning, execution, and reflection. We further introduce XGC-AVQuiz, the first benchmark aimed at comprehensively assessing MLLMs' understanding capabilities in both real-world and AI-generated scenarios. XGC-AVQuiz consists of 2,685 question-answer pairs across 20 tasks, with two key innovations: 1) AIGC Scenario Expansion: The benchmark includes 2,232 videos, comprising 1,102 professionally generated content (PGC), 753 user-generated content (UGC), and 377 AI-generated content (AIGC). These videos cover 10 major domains and 53 fine-grained categories. 2) Quality Perception Dimension: Beyond conventional tasks such as recognition, localization, and reasoning, we introduce a novel quality perception dimension. This requires MLLMs to integrate low-level sensory capabilities with high-level semantic understanding to assess audio-visual quality, synchronization, and coherence. Experimental results on XGC-AVQuiz demonstrate that current MLLMs struggle with quality perception and temporal alignment tasks. XGC-AVis improves these capabilities without requiring additional training, as validated on two benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23251 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | XGC-AVis: Towards Audio-Visual Content Understanding with a Multi-Agent Collaborative System Cao, Yuqin Min, Xiongkuo Gao, Yixuan Sun, Wei Zhang, Zicheng Han, Jinliang Zhai, Guangtao Multimedia Sound In this paper, we propose XGC-AVis, a multi-agent framework that enhances the audio-video temporal alignment capabilities of multimodal large models (MLLMs) and improves the efficiency of retrieving key video segments through 4 stages: perception, planning, execution, and reflection. We further introduce XGC-AVQuiz, the first benchmark aimed at comprehensively assessing MLLMs' understanding capabilities in both real-world and AI-generated scenarios. XGC-AVQuiz consists of 2,685 question-answer pairs across 20 tasks, with two key innovations: 1) AIGC Scenario Expansion: The benchmark includes 2,232 videos, comprising 1,102 professionally generated content (PGC), 753 user-generated content (UGC), and 377 AI-generated content (AIGC). These videos cover 10 major domains and 53 fine-grained categories. 2) Quality Perception Dimension: Beyond conventional tasks such as recognition, localization, and reasoning, we introduce a novel quality perception dimension. This requires MLLMs to integrate low-level sensory capabilities with high-level semantic understanding to assess audio-visual quality, synchronization, and coherence. Experimental results on XGC-AVQuiz demonstrate that current MLLMs struggle with quality perception and temporal alignment tasks. XGC-AVis improves these capabilities without requiring additional training, as validated on two benchmarks. |
| title | XGC-AVis: Towards Audio-Visual Content Understanding with a Multi-Agent Collaborative System |
| topic | Multimedia Sound |
| url | https://arxiv.org/abs/2509.23251 |