Model card
AudioCaps baseline (TopDown+Align).
Kim et al.open-sourceUnknown paramsVGGish + Top-Down attention + alignment loss1 current SOTA
Original AudioCaps paper baseline (NAACL 2019).
§ 01 · Benchmarks
Every benchmark AudioCaps baseline (TopDown+Align) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | AudioCaps | Audio · Audio Captioning | spider | 0.4% | #1 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where AudioCaps baseline (TopDown+Align) actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
editorial
1
result
0 of 1 rows marked verified.