GAIA: Rethinking Action Quality Assessment for AI-Generated Videos

arXiv:2406.06087v1 Announce Type: new
Abstract: Assessing action quality is both imperative and challenging due to its significant impact on the quality of AI-generated videos, further complicated by the inherently ambiguous nature of actions within AI-generated video (AIGV). Current action quality assessment (AQA) algorithms predominantly focus on actions from real specific scenarios and are pre-trained with normative action features, thus rendering them inapplicable in AIGVs. To address these problems, we construct GAIA, a Generic AI-generated Action dataset, by conducting a large-scale …

abstract action ai-generated video ai-generated videos algorithms arxiv assessment cs.cv current focus generated impact nature quality type video videos