Six Navers Lab / Einsia benchmarks and the work they test
Compare the tasks, scoring and evidence behind six Einsia benchmarks, with complete Radar detail pages and original references.
Model reports
MER2026 MER-FG
Track 2 of the MER2026 challenge: open-vocabulary, fine-grained emotion recognition from video, audio and subtitles, ranked on a 1,000-sample test set with emotion-wheel-based metrics that group synonyms (happy and joyful count as one label). Because the label space is open, how a system normalizes its vocabulary onto the wheel moves the score independently of recognition. Reference labels were built by merging top MER2025 team predictions and then manually validated.
Evidence available for this benchmark
Numeric results have not been collected for this source record. Use the paper, code or dataset below to check the task and experiments; this does not imply that the original work contains no results.
Start with these resources
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2026-04-21
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.