Paper Detail

SceneBind: Binding What and Where Across Vision, Audio and Language

Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu, Eli Shlizerman

arxiv Score 8.2

Published 2026-07-16 · First seen 2026-07-17

General AI

Abstract

We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explicitly captures object-level semantics, spatial attributes, and uncertainty. We further propose SceneBind Matching, a semantic-spatial matching scheme that integrates global scene similarity with object alignment, supporting cross-modal scene retrieval and object grounding. To train and evaluate SceneBind, we curate a novel real-world binaural audio-visual dataset with structured semantic and spatial annotations, and propose a training protocol for aligning semantic and spatial signals across modalities. SceneBind is compatible with large-scale pretrained semantic encoders, adds lightweight spatial modeling with only a few additional tokens. It achieves state-of-the-art scene and spatial retrieval while enabling strong zero-shot transfer to downstream tasks such as audio-visual localization.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{chen2026scenebind,
  title = {SceneBind: Binding What and Where Across Vision, Audio and Language},
  author = {Mingfei Chen and Zijun Cui and Ruoke Zhang and Hyeonggon Ryu and Eli Shlizerman},
  year = {2026},
  abstract = {We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explic},
  url = {https://arxiv.org/abs/2607.15265},
  keywords = {cs.CV, cs.AI, cs.MM, cs.SD, Computer science, Artificial intelligence, Embedding, Semantics (computer science), Object (grammar)},
  eprint = {2607.15265},
  archiveprefix = {arXiv},
}

Metadata

{}