Early-stage researcher applying continual and multimodal learning to computer-vision crop phenotyping and leaf counting.
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-21) 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—
No output score is computed yet. The OpenAlex snapshot indexes only one 2026 work, with h-index and i10-index both recorded as 0, so cumulative publication volume cannot be meaningfully assessed. This axis would measure total and per-year research output.
Impact—
No impact score is computed yet. With only one indexed work and no citation aggregates available in the snapshot, citation-based influence cannot be judged. This axis would measure citations, uptake, and scholarly influence of the researcher's work.
Focus100/100
Focus scores 100/100: the single field-classified work falls entirely under computer vision / agricultural plant phenotyping, and OpenAlex topics cluster tightly around smart agriculture and AI, plant nutrient uptake and metabolism, and greenhouse technology and climate control — one coherent applied vision-for-agriculture agenda, though grounded in very few papers.
Collaboration46/100
Collaboration scores 46/100, with nine distinct co-authors in the snapshot. On both cataloged 2026 preprints he sits in the last author position without the corresponding-author flag. The recurring pool includes Karanvir Singh, Theo Morales, Binh-Son Hua, Ruchi Bhatt, Pratibha Kumari, Shreya Bansal, Vedant Agnihotri and Dwarikanath Mahapatra.
Activity20/100
Activity scores 20/100: the snapshot records one work in the last three years, with all indexed output concentrated in 2026 (one publication). This is an early, thin record — the low score reflects minimal visible output so far rather than a long-term slowdown.
Reproducibility55/100
Reproducibility scores 55/100, computed from one assessed paper. For MCLC-NET, Evolve rates reproducibility readiness as medium: the model and the new RGB/depth/thermal field dataset are promising, but the review flags test-set tuning and metric inconsistencies as undermining confidence in the reported results.
Research summary
Mukesh Saini is an early-stage researcher whose visible output sits at the intersection of computer vision and agricultural plant phenotyping. The OpenAlex-resolved record indexes one work in 2026, and Evolve's catalog additionally tracks two arXiv preprints from that year: 'MCLC-NET: Multimodal Continual Learning for Leaf Counting' and 'Evaluating Mesh Reconstruction Methods for Crop Phenotyping'. On both he appears in the last author position without a corresponding-author flag, a placement often associated with senior or supervisory contributions. MCLC-NET proposes what Evolve's review describes as the first multimodal continual-learning leaf counter, together with a new RGB/depth/thermal field dataset; the review finds the results promising but notes that test-set tuning and metric inconsistencies weaken the claims, and rates reproducibility readiness as medium, feeding a reproducibility score of 55 from one assessed paper. His topical footprint is tightly clustered — smart agriculture and AI, plant nutrient uptake and metabolism, and greenhouse technology and climate control — producing a maximal focus score of 100. Collaboration is moderate (46) with nine distinct co-authors, while activity is low (20), reflecting one work in the last three years. Output- and impact-based scores are not yet computed, consistent with h-index and i10-index of 0 in the current snapshot.
Collaboration pattern
His visible collaboration network contains nine distinct co-authors. Recurring names across the record include Karanvir Singh, Theo Morales, Binh-Son Hua, Ruchi Bhatt, Pratibha Kumari, Shreya Bansal, Vedant Agnihotri and Dwarikanath Mahapatra. On both cataloged 2026 preprints he appears as last author without the corresponding-author flag, a pattern consistent with a senior or supervisory role, though two papers are too thin a base to confirm it. Collaboration score: 46/100.
Research keywords
Highlights
First multimodal continual-learning leaf counter
New RGB/depth/thermal field dataset for leaf counting
Benchmarking mesh reconstruction for crop phenotyping
In 'Evaluating Mesh Reconstruction Methods for Crop Phenotyping' (2026), he contributes to a systematic comparison of mesh reconstruction methods as applied to crop phenotyping, in the last author position.
Timeline
- 2026Publishes MCLC-NET on arXiv, proposing the first multimodal continual-learning leaf counter along with a new RGB/depth/thermal field dataset.
- 2026Contributes as last author to 'Evaluating Mesh Reconstruction Methods for Crop Phenotyping', a comparison of mesh reconstruction methods for plant phenotyping on arXiv.
- 2026Enters the Evolve catalog with two 2026 arXiv preprints, both situated in computer vision / agricultural plant phenotyping.
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.
- All bibliometrics derive from a single OpenAlex snapshot; no ORCID, institution, or country was available for identity confirmation.
- Output and impact scores are not computed: the snapshot indexes only one 2026 work, with h-index and i10-index recorded as 0.
- Evidence covers two 2026 arXiv preprints; peer-reviewed versions, grants, and awards are out of scope.
- 'Mukesh Saini' is a relatively common name; this profile is name-resolved from public bibliographic data and may merge or split identities.