Rohit Saluja
9 papers · 2022–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) 🏆 Keyword Champion (2) ❓ The Questioner
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Computer Vision
(5)
Machine Learning
(5)
Deep Learning
(4)
Application Areas
(3)
Learning Types · Machine Learning
(3)
Processing
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Analysis
(2)
Architectures
(2)
Resources & Methods
(2)
Core AI
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Keywords
semantic segmentation
(2)
difficulty estimation
(2)
multilingual model
(2)
domain adaptation
(2)
object detection
(2)
item response theory
(1)
few-shot learning
(1)
catastrophic forgetting
(1)
self-supervised learning
(1)
handwritten text recognition
(1)
attention mechanism
(1)
historical manuscripts
(1)
adversarial learning
(1)
incremental learning
(1)
iterative refinement
(1)
curriculum learning
(1)
feature representation
(1)
synthetic data augmentation
(1)
image-to-image translation
(1)
image restoration
(1)
Papers
Do Tokenizers Fail on Informal Hindi Expressions? Evidence from Static, Downstream, and Robustness Analyses
EACL 2026
AnciDev: A Dataset for High-Accuracy Handwritten Text Recognition of Ancient Devanagari Manuscripts
AACL 2025
HiLearners: Non-Native Spoken Hindi Error Correction
IJCNLP 2025
INDRA: Iterative Difficulty Refinement Attention for MCQ Difficulty Estimation for Indic Languages
AACL 2025
Multi-Feature Graph Convolution Network for Hindi OCR Verification
AACL 2025
TEEMIL : Towards Educational MCQ Difficulty Estimation in Indic Languages
COLING 2025
FLUID: Few-Shot Self-Supervised Image Deraining
WACV 2022
Multi-Domain Incremental Learning for Semantic Segmentation
WACV 2022
To Miss-Attend Is to Misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors
WACV 2022