# Multi-sound source localization on MUSIC-Duet (test) Source: [Multi-sound source localization on MUSIC-Duet (test)]() Collection index: [llms.txt]() Data updated: 2026-04-10T00:25:32.806Z Evaluation of Multi-sound source localization performance on the test split of the MUSIC-Duet dataset, using metrics including CAP, PIAP, CIoU@0.3, and AUC. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Multi-sound source localization | | Dataset (including any stated split) | MUSIC-Duet (test) | | Metric | CIoU@0.3 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 37 of 37 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [CIoU@0.3](): Higher is better; unit: PERCENT. - [CAP](): Higher is better; unit: PERCENT. - [PIAP](): Higher is better; unit: PERCENT. - [AUC](): Higher is better; unit: PERCENT. ## Recorded results | Method | CIoU@0.3 | Result date | Report paper | | --- | --- | --- | --- | | Generation-Analysis-Refinement | 82.7 | Not recorded | 69d732b97d0172140ec76d09 | | Generation-Analysis-Refinement | 80.8 | Not recorded | 69d732b97d0172140ec76d09 | | Qwen2.5-Omni | 50.6 | Not recorded | 69d732b97d0172140ec76d09 | | OA-SSL | 45.9 | Not recorded | 69d732b97d0172140ec76d09 | | T-VSL | 43.2 | Not recorded | 68fa73fd1e209131cea5f120 | | AVGN | 39.3 | Not recorded | 68fa73fd1e209131cea5f120 | | DSOL | 38.8 | Not recorded | 68fa73fd1e209131cea5f120 | | Proposed Method | 38.6 | Not recorded | 68fa72d01e209131cea58af0 | | NoPrior | 38.6 | Not recorded | 69d732b97d0172140ec76d09 | | Alignment | 38.3 | Not recorded | 68fa73fd1e209131cea5f120 | | Mix-and-Localize | 38.1 | Not recorded | 68fa73fd1e209131cea5f120 | | FNAC | 37.9 | Not recorded | 68fa73fd1e209131cea5f120 | | AudioCLIP | 36.9 | Not recorded | 68fa73fd1e209131cea5f120 | | MarginNCE | 36.1 | Not recorded | 68fa73fd1e209131cea5f120 | | EZ-VSL | 34.3 | Not recorded | 68fa73fd1e209131cea5f120 | | LVS | 33.1 | Not recorded | 68fa73fd1e209131cea5f120 | | AVGN | 32.5 | Not recorded | 68fa72d01e209131cea58af0 | | AVGN | 32.5 | Not recorded | 69d732b97d0172140ec76d09 | | Wav2CLIP | 32.2 | Not recorded | 68fa73fd1e209131cea5f120 | | CoarsetoFine | 31.8 | Not recorded | 68fa73fd1e209131cea5f120 | | DSOL | 30.1 | Not recorded | 68fa72d01e209131cea58af0 | | OTS | 29.4 | Not recorded | 68fa73fd1e209131cea5f120 | | MiniCPM-o | 27.7 | Not recorded | 69d732b97d0172140ec76d09 | | Mix-and-Localize | 26.5 | Not recorded | 68fa72d01e209131cea58af0 | | Mix-and-Localize | 26.5 | Not recorded | 69d732b97d0172140ec76d09 | | EZ-VSL | 24.3 | Not recorded | 68fa72d01e209131cea58af0 | | EZ-VSL | 24.3 | Not recorded | 69d732b97d0172140ec76d09 | | LVS | 22.5 | Not recorded | 68fa72d01e209131cea58af0 | | Attention10k | 21.6 | Not recorded | 68fa72d01e209131cea58af0 | | Attention 10k | 21.6 | Not recorded | 69d732b97d0172140ec76d09 | | InteractiveOmni | 20 | Not recorded | 69d732b97d0172140ec76d09 | | CoarseToFIne | 17.6 | Not recorded | 68fa72d01e209131cea58af0 | | CoarseToFine | 17.6 | Not recorded | 69d732b97d0172140ec76d09 | | DMC | 17.5 | Not recorded | 68fa72d01e209131cea58af0 | | DMC | 17.5 | Not recorded | 69d732b97d0172140ec76d09 | | OTS | 13.3 | Not recorded | 68fa72d01e209131cea58af0 | | OTS | 13.3 | Not recorded | 69d732b97d0172140ec76d09 | ### Generation-Analysis-Refinement CIoU@0.3: 82.7. Result ID: 69d8436347f34ce924c057ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"MLLMs","N iterations":"5"}. This record does not assert independent reproduction. ### Generation-Analysis-Refinement CIoU@0.3: 80.8. Result ID: 69d8436347f34ce924c057ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"MLLMs","N iterations":"3"}. This record does not assert independent reproduction. ### Qwen2.5-Omni CIoU@0.3: 50.6. Result ID: 69d8436347f34ce924c057aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"MLLMs"}. This record does not assert independent reproduction. ### OA-SSL CIoU@0.3: 45.9. Result ID: 69d8436347f34ce924c057a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### T-VSL CIoU@0.3: 43.2. Result ID: 699327f73a6c314849141baa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoders":"AudioCLIP (ResNet-50 + ESResNeXt)"}. This record does not assert independent reproduction. ### AVGN CIoU@0.3: 39.3. Result ID: 699327f73a6c314849141ba7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### DSOL CIoU@0.3: 38.8. Result ID: 699327f73a6c314849141ba6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### Proposed Method CIoU@0.3: 38.6. Result ID: 69a15ef035dfcabb00e69b07. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NoPrior CIoU@0.3: 38.6. Result ID: 69d8436347f34ce924c057a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### Alignment CIoU@0.3: 38.3. Result ID: 699327f73a6c314849141ba4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### Mix-and-Localize CIoU@0.3: 38.1. Result ID: 699327f73a6c314849141ba5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### FNAC CIoU@0.3: 37.9. Result ID: 699327f73a6c314849141ba3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### AudioCLIP CIoU@0.3: 36.9. Result ID: 699327f73a6c314849141ba8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### MarginNCE CIoU@0.3: 36.1. Result ID: 699327f73a6c314849141ba2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### EZ-VSL CIoU@0.3: 34.3. Result ID: 699327f73a6c314849141ba1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### LVS CIoU@0.3: 33.1. Result ID: 699327f73a6c314849141ba0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### AVGN CIoU@0.3: 32.5. Result ID: 69a15ef035dfcabb00e69b06. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AVGN CIoU@0.3: 32.5. Result ID: 69d8436347f34ce924c057a7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### Wav2CLIP CIoU@0.3: 32.2. Result ID: 699327f73a6c314849141ba9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### CoarsetoFine CIoU@0.3: 31.8. Result ID: 699327f73a6c314849141b9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### DSOL CIoU@0.3: 30.1. Result ID: 69a15ef035dfcabb00e69b02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OTS CIoU@0.3: 29.4. Result ID: 699327f73a6c314849141b9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoders":"AudioCLIP pre-trained"}. This record does not assert independent reproduction. ### MiniCPM-o CIoU@0.3: 27.7. Result ID: 69d8436347f34ce924c057ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"MLLMs"}. This record does not assert independent reproduction. ### Mix-and-Localize CIoU@0.3: 26.5. Result ID: 69a15ef035dfcabb00e69b05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mix-and-Localize CIoU@0.3: 26.5. Result ID: 69d8436347f34ce924c057a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### EZ-VSL CIoU@0.3: 24.3. Result ID: 69a15ef035dfcabb00e69b04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### EZ-VSL CIoU@0.3: 24.3. Result ID: 69d8436347f34ce924c057a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### LVS CIoU@0.3: 22.5. Result ID: 69a15ef035dfcabb00e69b03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Attention10k CIoU@0.3: 21.6. Result ID: 69a15ef035dfcabb00e69afe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Attention 10k CIoU@0.3: 21.6. Result ID: 69d8436347f34ce924c057a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### InteractiveOmni CIoU@0.3: 20. Result ID: 69d8436347f34ce924c057ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"MLLMs"}. This record does not assert independent reproduction. ### CoarseToFIne CIoU@0.3: 17.6. Result ID: 69a15ef035dfcabb00e69b01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CoarseToFine CIoU@0.3: 17.6. Result ID: 69d8436347f34ce924c057a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### DMC CIoU@0.3: 17.5. Result ID: 69a15ef035dfcabb00e69b00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DMC CIoU@0.3: 17.5. Result ID: 69d8436347f34ce924c057a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. ### OTS CIoU@0.3: 13.3. Result ID: 69a15ef035dfcabb00e69aff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OTS CIoU@0.3: 13.3. Result ID: 69d8436347f34ce924c057a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model category":"Vision Model"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.