{"type":"ScholarlyArticle","title":"Listen and Count: Expanding the Frontier of Zero-shot Object Counting to Sound-centric Counting","authors":[{"name":"Mingjie Wang","slug":"mingjie-wang","given":"Mingjie","family":"Wang","affiliation":""},{"name":"Zhuohang Li","slug":"zhuohang-li","given":"Zhuohang","family":"Li","affiliation":""},{"name":"Qi Zhang","slug":"qi-zhang","given":"Qi","family":"Zhang","affiliation":""},{"name":"Jun Zhou","slug":"jun-zhou","given":"Jun","family":"Zhou","affiliation":""},{"name":"Zili Yi","slug":"zili-yi","given":"Zili","family":"Yi","affiliation":""},{"name":"Minglun Gong","slug":"minglun-gong","given":"Minglun","family":"Gong","affiliation":""}],"abstract":"While class-agnostic object counting has recently evolved from image-exemplar to language-guided paradigms, existing methods are limited by text polysemy and the lack of prompts in audio-sensing scenarios. To overcome these challenges, we introduce a sound-centric counting paradigm, enabling models to \"listen and count\" using the vivid and discriminative signatures of sound cues. We propose S2ICount, which achieves seamless, fine-grained audio-visual alignment for sound-guided counting. At its core, SoundMamba leverages linear-complexity long-range semantic modelling to align cross-modal features, while the Sound Calibration Module designs a circular scanning mechanism to progressively reconcile modality discrepancies using multi-scale cues from a Stable Diffusion backbone. To enhance saliency awareness, a Multi-tier Hybrid Optimization strategy enforces consistency across magnitude, semantics, and distribution. In addition, we introduce SoundCount, the first large-scale sound-oriented counting dataset, comprising over 2,000 scenes and 1,650 audio sources across 66 object categories. Extensive experiments demonstrate that S2ICount achieves state-of-the-art performance, validating the effectiveness of sound as a robust guidance modality for counting.  The dataset, demo and implementation code are made publicly accessible at https://github.com/ZSTU-CV-Lab/S2ICount.","doi":"10.24963/ijcai.2026/194","url":"https://ijcai.org/proceedings/2026/194","pdf":"https://ijcai.org/proceedings/2026/0194.pdf","markdown":"https://ijcai.org/proceedings/2026/194.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/194","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":194,"pages":{"first":1740,"last":1748},"keywords":["Computer Vision: Scene analysis and understanding","Computer Vision: Applications and Systems","Computer Vision: Multimodal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}