Pith. sign in

Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio. However, the progress in these directions has been mostly focused on tasks that only require a coarse-grained understanding of the audio-visual semantics. We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio both spatially and temporally. With a new modality alignment module based on optimal transport and a cross-attention module that enforces audio-visual consistency, Meerkat can tackle challenging tasks such as audio referred image grounding, image guided audio temporal localization, and audio-visual fact-checking. Moreover, we carefully curate a large dataset AVFIT that comprises 3M instruction tuning samples collected from open-source datasets, and introduce MeerkatBench that unifies five challenging audio-visual tasks. We achieve state-of-the-art performance on all these downstream tasks with a relative improvement of up to 37.12%.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues cs.CV · 2024-12-19 · conditional · none · ref 16 · internal anchor

    EarthDial is a 4B-parameter remote sensing chatbot trained on 11.11M instruction pairs to handle multi-resolution, multi-spectral, and multi-temporal satellite imagery, and it reports gains over prior VLMs on dozens of EO benchmarks.