Anil Batra
Scholar

Anil Batra

Google Scholar ID: C9rsD2UAAAAJ
University of Edinburgh
Computer VisionMachine LearningVision and LanguageNatural Language Processing
Citations & Impact
All-time
Citations
379
 
H-index
4
 
i10-index
3
 
Publications
10
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Paper 'Predicting Implicit Arguments in Procedural Video Instructions' accepted at ACL 2025 (Main Conference, May 2025)
  • Paper 'Efficient Pre-training for Localized Instruction Generation of Videos' accepted at ECCV 2024 (July 2024)
  • Paper 'Temporal Ordering in the Segmentation of Instructional Videos' accepted at BMVC 2022 (September 2022)
  • Paper on 'Improved Road Connectivity' accepted at CVPR 2019 (March 2019)
  • Paper on 'Self-Supervised Learning' accepted at BMVC 2018 (June 2018)
  • Poster presentation at CVPR 2019 (June 2019)
  • Served as session chair volunteer at LXAI Workshop, NeurIPS 2021 (December 2021)
  • Served as reviewer for CVPR 2022 (November 2021)
  • Served as reviewer for ICCV 2021 (June 2021)
  • Successfully defended Master’s thesis titled 'Road Topology Extraction from Satellite images by Knowledge Sharing' (June 2019)
Education
  • Ph.D. scholar in the School of Informatics, University of Edinburgh, under the CDT-NLP program (joined September 2020)
  • Supervised by Prof. Frank Keller, Prof. Marcus Rohrbach, and Dr. Laura Sevilla
  • Completed Master of Computer Science (by research) at IIIT-Hyderabad
  • Master’s advisors: Prof. C.V. Jawahar, with mentorship from Facebook researchers Dr. Guan Pang and Dr. Saikat Basu
  • Member of the Center for Visual Information Technology (CVIT) Lab during Master’s
Background
  • Research interests lie at the intersection of Language and Vision
  • Focuses on developing models that can plan, reason, and execute goal-oriented tasks involving multiple complex events through text comprehension and video analysis
  • Current work involves analyzing long procedural videos and text to understand and ground the temporal structure of events
  • Aims to develop efficient models that accurately capture event sequences and timing to enhance real-world task performance
  • Also interested in Geospatial data, large language models, and improving model reliability