Mohsen Fayyaz
14 papers · 2018–2026 · 8 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 ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (30)
🧬
Topic Evolution
🗃️
Keyword Collector
(61)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
🚀
Conference Pioneer
Top co-authors
Research topics
Machine Learning
(8)
Deep Learning
(7)
Architectures
(5)
Core Methods
(5)
Artificial Intelligence
(4)
Natural Language Processing
(4)
Computer Vision
(3)
Application Areas
(3)
Applications
(3)
Core AI
(3)
Learning Types
(3)
Analysis
(2)
Generation
(2)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Keywords
retrieval-augmented generation
(2)
layer-wise analysis
(2)
action recognition
(2)
benchmark evaluation
(1)
video classification
(1)
self-supervised learning
(1)
temporal modeling
(1)
knowledge transfer
(1)
weakly supervised learning
(1)
relation extraction
(1)
cross-lingual transfer
(1)
multi-label classification
(1)
video understanding
(1)
model analysis
(1)
contextual representation
(1)
semantic knowledge
(1)
linguistic knowledge
(1)
probing analysis
(1)
dense retrieval
(1)
attention mechanism
(1)
Papers
Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices
WACV 2026
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence
ACL 2025
MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
ICLR 2025
Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding
ECCV 2024
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
ACL 2023
Adaptive Token Sampling for Efficient Vision Transformers
ECCV 2022
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
NAACL 2022
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
ACL 2022
3D CNNs With Adaptive Temporal Feature Resolutions
CVPR 2021
Long Short View Feature Decomposition via Contrastive Video Representation Learning
ICCV 2021
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
EMNLP 2021
Large Scale Holistic Video Understanding
ECCV 2020
SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation
CVPR 2020
Spatio-Temporal Channel Correlation Networks for Action Classification
ECCV 2018