Publications

• Temporal Object-Aware Vision Transformer for Few-Shot Video Object Detection
  Yogesh Kumar, Anand Mishra
  AAAI 2026 (Main Track)
  [Paper] | [Code]
  

• Aligning Moments in Time using Video Queries
  Yogesh Kumar, Uday Agarwal, Manish Gupta, Anand Mishra
  ICCV 2025
  [Paper] | [Code] | [Data]
  

• Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing
  Yogesh Kumar
  EMNLP 2025 (Main Track)
  [Paper] | [Code]
  

• Chapter-Based Video Moment Retrieval using Natural Language Queries
  Uday Agarwal, Yogesh Kumar, Abu Shahid, Prajwal Gatti, Manish Gupta, Anand Mishra
  ICVGIP 2024
  [Paper] | [Code] | [Data]
  

• QDETRv: Query-Guided DETR for One-Shot Object Localization in Videos
  Yogesh Kumar, Saswat Mallick, Anand Mishra, Sowmya Rasipuram, Anutosh Maitra, and Roshni Ramnani
  AAAI 2024 (Main Track)
  [Paper] | [Code] | [Project]
  

• Few-Shot Referring Relationships in Videos
  Yogesh Kumar, Anand Mishra
  CVPR 2023
  [Paper] | [Code] | [Project]
  

• Towards Making Flowchart Images Machine Interpretable
  Shreya Shukla, Prajwal Gatti, Yogesh Kumar, Vikash Yadav, Anand Mishra
  ICDAR 2023
  [Paper] | [Code] | [Project]