Taneshq Gupta

B.Tech Computer Science & Engineering · IIT Mandi
§1 — Education

Academic Record

IIT Mandi Aug 2024 – May 2028
Bachelor of Technology in Computer Science and Engineering HP · INDIA
8.29 CGPA
Till 4th Semester
Central Board of Secondary Education
Modern Convent School DL · INDIA
96.0% Class XII · 2024
95.6% Class X · 2022
§2 — Projects

Selected Work

Biometric Segmentation Research: Concurrent Squeeze-Excitation Accepted · IEEE IJCB 2026
Paper Accepted · IEEE IJCB 2026

M. Vitek et al. (incl. T. Gupta) — Label-Efficient Sclera Segmentation with Foundation Models: SSBC 2026

eCF Paper Id: IJCB2026-325

  • Architected a Vision-Language grounded segmentation model fusing a frozen CLIP ViT-B/32 text encoder with a LoRA-adapted DINOv2 ViT-S/14 backbone via a novel cross-attention grounding module, tuning only 3.19M of 88.3M parameters (3.6%).
  • Designed a multi-scale Feature Pyramid Network and Dense-CSSE decoder fusing DenseNet-style feature reuse with concurrent spatial-channel squeeze-excitation for pixel-precise boundary delineation.
  • Devised a two-model training strategy with real-data oversampling, lifting real-world F1 from 0.8795 to 0.9546 on MASD and 0.8664 to 0.9336 on SBVPI, against a 0.9771 synthetic validation F1.
  • Led a team of 10 for the SSBC 2026 Track 1 submission, training both regimes in under 3.5 hours on a single NVIDIA RTX A5000 24GB GPU.
MASD F1 — Synthetic-only → Mixed model0.8795 → 0.9546
SBVPI F1 — Synthetic-only → Mixed model0.8664 → 0.9336
Safe-Dash: Driver Drowsiness Detection
  • Collaborated with a cross-functional team of 8 peers to build an edge-AI system on an NVIDIA Jetson Nano using the MediaPipe Face Mesh pipeline.
  • Implemented a unified attention score derived from EAR, MAR, and 3D Head Pose Estimation.
  • Engineered a multi-modal alert engine: Visual (LCD), Audio (Voice), Haptic (Vibration).
  • Built a real-time fleet dashboard with Flask & Redis, visualizing telemetry at 5s intervals.
Skill Sharing Platform Web-App
  • Tech Stack: Rust, SvelteKit, Postgres, TailwindCSS, TypeScript, Cloudinary, Railway, OpenStreetMap, Axum, Tokio.
  • Installable as a PWA with PIN-code-based real-time map and 100+ category post filters; secure email auth with hashed passwords.
  • Dynamic + persistent theme switching across 5 themes, with a user-friendly profile picture change protocol.
Unified Campus Portal for Colleges
  • Engineered a unified campus PWA consolidating 4 fragmented institutional systems (Governance, Grievances, Academics, Opportunities), designed to scale for 3,000+ students and faculty.
  • Architected a highly concurrent, type-safe REST API using Rust and Axum delivering sub-50ms response times; secured 100% of endpoints via Google OAuth with strict RBAC across 4 user tiers.
  • Designed a PostgreSQL schema with UUID primary keys and 7+ custom ENUM types; implemented a 4-stage automated grievance workflow with real-time status tracking and audit logging.
  • Built a reactive, mobile-first frontend with Svelte and Vite, achieving a 100% PWA compliance score; cross-stack telemetry cut debugging time by 60%.
§3 — Achievements

Recognition & Certifications

Upper Intermediate — Level 4
Japanese · Grade A Fluency Certification

Awarded by IIT Mandi for reaching Grade A fluency at the Upper Intermediate (Level 4) tier of the institute's Japanese language program.

N5
JLPT N5
Official Certification · Japanese Language

Official Japanese-Language Proficiency Test certification at the N5 level.

§4 — Technical Skills

Tools & Technologies

Deep Learning

DINO CLIP Vision Transformers LoRA Cross-Attention FPN Squeeze-Excitation

Edge Computing & AI

SolidWorks (CAD) Jetson Nano/Xavier MediaPipe OpenCV TensorRT

Hosting & Domains

PWA / Service Workers Porkbun Railway Vercel Netlify Render Namecheap

Databases

PostgreSQL Redis (Time-series)

Languages

Python Rust C C++ Svelte Java SQL JavaScript TypeScript HTML/CSS

Libraries

PyTorch Pillow MediaPipe OpenStreetMap Axum Tokio Tailwind CSS pandas NumPy Matplotlib Chart.js