Early-career affective computing researcher: emotion recognition with missing and open-vocabulary modalities.
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
2
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-14) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: this axis measures publication volume and trajectory, but the name-resolved OpenAlex record is too sparse — five works since 2021, with no ORCID linkage — to support a confident output score.
Impact—
Not yet scored: citation-based impact cannot be assessed reliably here. This axis would measure citation counts, h-index momentum and influence on later work, but only h-index 2 and i10-index 1 exist — too little signal to score.
Focus0/100
Scores 0, indicating a dispersed topic profile. The field split is even (0.5/0.5) between two heavily overlapping affective-computing labels, and OpenAlex topic counts divide into five affect, sentiment and speech mentions versus three sensor-based localization ones. Both reviewed 2026 papers are strictly multimodal emotion recognition, so part of this dispersion — and the zero score — may reflect name-resolution noise rather than genuinely scattered research.
Collaboration39/100
Scores 39. The OpenAlex record lists 6 distinct co-authors, and the two Evolve-reviewed papers repeat a compact team — Yanbing Wang, Chunyang Yu, Yichi Zhang, Jing Luo and Xinyu Yang — with Chunyang Yu appearing on both entries. On both 2026 arXiv papers Wang is a middle author and not the corresponding author, consistent with a specialist contributor inside small, stable groups rather than an independent project lead.
Activity40/100
Scores 40. The indexed record shows a thin but persistent cadence: one work each in 2021, 2023 and 2024, then two in 2026, with recent3yWorks at 3. The 2026 pair — both arXiv preprints on multimodal emotion recognition reviewed by Evolve — is the densest cluster in the profile, suggesting an accelerating rhythm from a low base rather than a sustained high-output schedule.
Reproducibility55/100
Scores 55, the mean repro-readiness across the 2 Evolve-reviewed papers, both rated medium. BiCFlow-MER reports results on IEMOCAP, MELD and CASE, but its IEMOCAP gain (+0.4 WA) sits within fold variance and awaits independent verification; APCF shows strong gains when text is absent and marginal ones with all modalities present. Releasing code, configs and protocols would be the clearest path above medium.
Research summary
Shenyue Wang (Shanghai Liangyou, China) is an early-stage researcher in affective computing whose indexed work centers on multimodal emotion recognition. The bibliographic snapshot is name-resolved from OpenAlex without ORCID linkage and records five works across 2021, 2023, 2024 and 2026 (one, one, one and two respectively), three of them in the last three years. The field distribution splits evenly (0.5/0.5) between multimodal speech emotion recognition and multimodal machine learning, and topic counts add three localization-related mentions alongside five affect, sentiment and speech ones, so the profile reads as one focused line plus a secondary cluster. Evolve has reviewed two 2026 arXiv papers, on both of which Wang is a middle author: BiCFlow-MER, which orchestrates discriminative and generative multimodal emotion recognition via conditional transport and rectified flow, and APCF, affect-prototype-guided fusion for open-vocabulary recognition with missing modalities. Verdicts are cautiously positive — strong gains when text is absent for APCF, and IEMOCAP improvements of +0.4 WA within fold variance for BiCFlow-MER — leaving both promising but unverified. Radar scores are collaboration 39, activity 40, reproducibility 55 (mean over two papers) and focus 0, while output and impact are not scored for lack of data. An h-index of 2 and i10-index of 1 confirm a nascent citation record.
Collaboration pattern
Wang works within small, recurring teams: the OpenAlex record lists 6 distinct co-authors, and the Evolve-reviewed papers repeat Yanbing Wang, Chunyang Yu, Yichi Zhang, Jing Luo and Xinyu Yang, with Chunyang Yu appearing on both. On both 2026 arXiv papers Wang is a middle author and not corresponding, indicating a hands-on technical contributor within a stable group rather than a project lead. The collaboration dimension scores 39 on this basis.
Research keywords
Highlights
BiCFlow-MER: conditional transport unifies discriminative and generative MER
APCF: affect-prototype-guided fusion for incomplete, open-vocabulary MER
Timeline
- 2021Earliest indexed work appears in the OpenAlex countsByYear record (1 publication).
- 2023One indexed publication; output remains intermittent rather than year-on-year continuous.
- 2024One indexed publication, maintaining the low-frequency cadence.
- 2026Two works — the record's busiest year: both are arXiv preprints on multimodal emotion recognition reviewed by Evolve (BiCFlow-MER and APCF), with Wang as a middle author on each.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric counts come from a name-resolved OpenAlex profile; without an ORCID, homonyms may be merged or works missed.
- Only the two 2026 arXiv papers carry Evolve full-text verdicts; earlier works are represented by counts and topics only.
- Output and impact dimensions are unscored: citation and volume signals are too thin (h-index 2, i10-index 1).
- Radar scores use Evolve's internal 0-100 normalization and should not be compared across data sources.