Tanveer Hannan

Tanveer Hannan

PhD Student of AI

LMU Munich

Biography

I am a third-year PhD student in the Department of Computer Science at LMU Munich, where I have the privilege of working with Prof. Thomas Seidl and Prof. Gedas Bertasius. My main research focus is computer vision, video understanding, and large vision language modeling. Currently, I am working at Huawei Trustworthy Lab this summer as a Research Scientist Intern, focusing on the reliability and robustness of large vision language models.

Previously, I was a Machine Learning Intern at Hensoldt Analytics where I also did my Master’s Thesis. Also, I was a research assistant at MCML and Siemens. Before joining LMU Munich, worked as a software developer at Helical inc.

Recent News:

Interests
  • Vision Language Modeling
  • Computer Vision
  • Video Understanding
  • Reliable AI
  • Natural Language Processing
Education
  • PhD in Computer Science, 2022-Present

    LMU Munich

  • MSc in Data Science, 2019-2021

    LMU Munich

  • BSc in Computer Science and Engineering, 2014-2018

    Bangladesh University of Engineering and Technology

Experience

 
 
 
 
 
Huawei
Research Scientist Intern
July 2024 – Present Munich
Reliability of Large Vision Language Models
 
 
 
 
 
Hensoldt Analytics
Research Intern
July 2021 – December 2021 Munich
Multiple Object Tracking in Videos
 
 
 
 
 
MCML
Research Assistant
October 2020 – June 2021 Munich
Hierarchical Transformer for Object Detection
 
 
 
 
 
Siemens, Advanta
Student Intern
October 2020 – April 2021 Munich
Reinforcement Learning for Supply Chain Management
 
 
 
 
 
Helical Inc.
Software Engineer
November 2018 – August 2019 Munich
Software Developer

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos. In ArXiv.

PDF Cite Code

(2024). RGNet: A Unified Retrieval and Grounding Network for Long Videos. In ECCV.

PDF Cite Code Project

(2024). Context Matters: Leveraging Spatiotemporal Metadata for Semi-Supervised Learning on Remote Sensing Images . In ECAI.

PDF Cite

(2023). GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation. In ICPR.

PDF Cite Code

(2022). InstanceFormer: An Online Video Instance Segmentation Framework. In AAAI23.

PDF Cite Code Poster

Contact