StarVQA: Space-Time Attention for Video Quality Assessment
원문 초록
The attention mechanism is blooming in computer vision nowadays. However, its application to video quality assessment (VQA) has not been reported. Evaluating the quality of in-the-wild videos is challenging due to the unknown of pristine reference and shooting distortion. This paper presents a novel \underline{s}pace-\underline{t}ime \underline{a}ttention network fo\underline{r} the \underline{VQA} problem, named StarVQA. StarVQA builds a Transformer by alternately concatenating the divided space-time attention. To adapt the Transformer architecture for training, StarVQA designs a vectorized regression loss by encoding the mean opinion score (MOS) to the probability vector and embedding a special vectorized label token as the learnable variable. To capture the long-range spatiotemporal dependencies of a video sequence, StarVQA encodes the space-time position information of each patch to the input of the Transformer. Various experiments are conducted on the de-facto in-the-wild video datasets, including LIVE-VQC, KoNViD-1k, LSVQ, and LSVQ-1080p. Experimental results demonstrate the superiority of the proposed StarVQA over the state-of-the-art. Code and model will be available at: https://github.com/DVL/StarVQA.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results
Breaking Annotation Barriers: Generalized Video Quality Assessment via Ranking-based Self-Supervision
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment
AMD-Hummingbird: Towards an Efficient Text-to-Video Model
KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception
토론
이 논문과 연결된 포럼 글이 아직 없습니다.