OmniAVS is a new 2,104-video dataset with 8 multimodal expression types for referring audio-visual segmentation, and OISA is an MLLM baseline that outperforms prior methods on it.
TIM: A Time Interval Ma- chine for Audio-Visual Action Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
OmniAVS is a new 2,104-video dataset with 8 multimodal expression types for referring audio-visual segmentation, and OISA is an MLLM baseline that outperforms prior methods on it.