Faegheh Sardari
Scholar

Faegheh Sardari

Google Scholar ID: _8dV3CgAAAAJ
Senior Scientist at Microsoft
Computer VisionVideo Reasoning/UnderstandingMultimodal LearningLLMs3D Human Representation
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
126
 
H-index
7
 
i10-index
6
 
Publications
17
 
Co-authors
0
 
Contact
Emailf.sardari@surrey.ac.ukGitHubOpen ↗LinkedInOpen ↗
Publications
5 items
DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding
2025
Cited
0
TEn-CATS: Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
2025
Cited
0
TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing
2025
Cited
0
Deconstruct Complexity (DeComplex): A Novel Perspective on Tackling Dense Action Detection
2025
Cited
0
NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative
arXiv.org · 2024
Cited
3
Resume (English only)
Academic Achievements
  • Paper 'NarrativeBridge' accepted at ICLR 2025
  • Secured a £100K grant in February 2025 (50% EPSRC, 50% Tesco) to advance video understanding for retail
  • Published 'CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing' at ECCV 2024
  • Released 'Reframing Dense Action Detection (RefDense)' on arXiv in 2025
  • Contributed to the multi-view audio-visual dataset ForecasterFlexOBM, published at ICME 2024
Co-authors
0 total
Co-authors: 0 (list not available)