Vijay Mahadevan
16 papers · 2007–2024 · 7 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (40) π Academic Marathon Β· Full π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Keyword Champion
π§
Keyword Pioneer
π
Keyword Trendsetter Combo
(5)
π§¬
Topic Evolution
π
Trend Setter
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(89)
Top co-authors
Research topics
Computer Vision
(12)
Machine Learning
(10)
Deep Learning
(9)
Artificial Intelligence
(8)
Core AI Β· Artificial Intelligence
(8)
Analysis
(7)
Architectures
(6)
Core Methods
(6)
Application Areas
(4)
Core AI Β· Computer Vision
(4)
Learning Types
(4)
Processing
(3)
Data Science & Analytics
(2)
Interdisciplinary
(2)
Cognitive Science
(2)
Keywords
cross-modal retrieval
(2)
transformer architecture
(2)
vision-language model
(2)
visual attention
(2)
knowledge distillation
(2)
attention mechanism
(2)
dimensionality reduction
(2)
saliency detection
(2)
encoder-decoder transformer
(2)
multimodal learning
(2)
visual saliency
(2)
background subtraction
(1)
feature learning
(1)
temporal dynamics
(1)
scene understanding
(1)
multi-task learning
(1)
feature extraction
(1)
semidefinite programming
(1)
large margin learning
(1)
named entity recognition
(1)
Papers
DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models
NAACL 2024
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models
EMNLP 2024
Enhancing Vision-Language Pre-training with Rich Supervisions
CVPR 2024
Multiple-Question Multiple-Answer Text-VQA
NAACL 2024
No Head Left Behind β Multi-Head Alignment Distillation for Transformers
AAAI 2024
DocTr: Document Transformer for Structured Information Extraction in Documents
ICCV 2023
PolyFormer: Referring Image Segmentation As Sequential Polygon Generation
CVPR 2023
End-to-End Piece-Wise Unwarping of Document Images
ICCV 2021
LayoutTransformer: Layout Generation and Completion With Self-Attention
ICCV 2021
Visual Relationship Detection Using Part-and-Sum Transformers With Composite Queries
ICCV 2021
VLAD3: Encoding Dynamics of Deep Features for Action Recognition
CVPR 2016
Cluster Canonical Correlation Analysis
AISTATS 2014
Learning Optimal Seeds for Diffusion-based Salient Object Detection
CVPR 2014
On the connections between saliency and tracking
NeurIPS 2012
Maximum Covariance Unfolding : Manifold Learning for Bimodal Data
NeurIPS 2011
The discriminant center-surround hypothesis for bottom-up saliency
NeurIPS 2007