Publications

2026

1. 

   Forget, Anticipate and Adapt: Test Time Training for Long Videos

   Rajat Modi, S. Noel, Xin Liang, and Yogesh S. Rawat

   In European Conference on Computer Vision (ECCV), 2026

   ECCV arXiv Bib Code

   @inproceedings{modi2026forget,
     title = {Forget, Anticipate and Adapt: Test Time Training for Long Videos},
     author = {Modi, Rajat and Noel, S. and Liang, Xin and Rawat, Yogesh S.},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2026},
   }

2. 

   Robust Onion: Peeling Open Vocab Object Detectors Under Noise

   Priyank Pathak, M. Karuppasamy, A. Baranwal, Shruti Vyas, and Yogesh S. Rawat

   In European Conference on Computer Vision (ECCV), 2026

   ECCV arXiv Bib Code Website

   @inproceedings{pathak2026onion,
     title = {Robust Onion: Peeling Open Vocab Object Detectors Under Noise},
     author = {Pathak, Priyank and Karuppasamy, M. and Baranwal, A. and Vyas, Shruti and Rawat, Yogesh S.},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2026},
   }

3. 

   CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates

   Shresth Grover, Priyank Pathak, Akash Kumar, and Yogesh S. Rawat

   In European Conference on Computer Vision (ECCV), 2026

   ECCV arXiv Bib Supp Code Website

   @inproceedings{grover2026cosplan,
     title = {CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates},
     author = {Grover, Shresth and Pathak, Priyank and Kumar, Akash and Rawat, Yogesh S.},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2026},
   }

4. 

   Learning to Deny: Action Denial in Multimodal Large Language Models

   Raiyaan Abdullah, Shehreen Azad, and Yogesh Singh Rawat

   In European Conference on Computer Vision (ECCV), 2026

   ECCV arXiv Bib Code

   @inproceedings{abdullah2026deny,
     title = {Learning to Deny: Action Denial in Multimodal Large Language Models},
     author = {Abdullah, Raiyaan and Azad, Shehreen and Rawat, Yogesh Singh},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2026},
   }

5. 

   StreamReady: Learning What to Answer and When in Long Streaming Videos

   Shehreen Azad, Vibhav Vineet, and Yogesh Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   CVPR arXiv Bib PDF Code Website

   @inproceedings{azad2026streamready,
     title = {StreamReady: Learning What to Answer and When in Long Streaming Videos},
     author = {Azad, Shehreen and Vineet, Vibhav and Rawat, Yogesh},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {40494--40504},
     year = {2026},
   }

6. 

   Sky2Ground: A Benchmark for Site Modeling under Varying Altitude

   Zengyan Wang, Sirshapan Mitra, Rajat Modi, Hui Xian Grace Lim, and Yogesh S. Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   CVPR arXiv Bib

   @inproceedings{wang2026sky2ground,
     title = {Sky2Ground: A Benchmark for Site Modeling under Varying Altitude},
     author = {Wang, Zengyan and Mitra, Sirshapan and Modi, Rajat and Lim, Hui Xian Grace and Rawat, Yogesh S.},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2026},
   }

7. 

   ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction

   Sirshapan Mitra and Yogesh S. Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026

   CVPR Findings arXiv Bib Video

   @inproceedings{mitra2026prodig,
     title = {ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction},
     author = {Mitra, Sirshapan and Rawat, Yogesh S.},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings},
     year = {2026},
   }

8. 

   RobustGait: Robustness Analysis for Appearance Based Gait Recognition

   Reeshoon Sayera, Akash Kumar, Sirshapan Mitra, Prudvi Kamtam, and Yogesh S Rawat

   In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

   WACV arXiv Bib Code Poster Website

   @inproceedings{sayera2026robustgait,
     title = {RobustGait: Robustness Analysis for Appearance Based Gait Recognition},
     author = {Sayera, Reeshoon and Kumar, Akash and Mitra, Sirshapan and Kamtam, Prudvi and Rawat, Yogesh S},
     booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
     pages = {2541--2552},
     year = {2026},
   }

9. 

   ACuRE: Accurate Continuity-Regularized SpO2 Estimation Using Liquid Time-Constant Networks

   Shahzad Ahmad, Divya Mishra, Sania Bano, Sukalpa Chanda, and Yogesh Singh Rawat

   In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

   Bib

   @inproceedings{ahmad2026acure,
     title = {ACuRE: Accurate Continuity-Regularized SpO2 Estimation Using Liquid Time-Constant Networks},
     author = {Ahmad, Shahzad and Mishra, Divya and Bano, Sania and Chanda, Sukalpa and Rawat, Yogesh Singh},
     booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
     pages = {7250--7259},
     year = {2026},
   }

10. 

    VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning

    Chaoyang Wang, Wenrui Bao, Sicheng Gao, Bingxin Xu, Yu Tian, Yogesh S Rawat, Yunhao Ge, and Yuzhang Shang

    arXiv preprint arXiv:2603.14523, 2026

    arXiv Bib

    @article{wang2026vla,
      title = {VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning},
      author = {Wang, Chaoyang and Bao, Wenrui and Gao, Sicheng and Xu, Bingxin and Tian, Yu and Rawat, Yogesh S and Ge, Yunhao and Shang, Yuzhang},
      journal = {arXiv preprint arXiv:2603.14523},
      year = {2026},
    }

11. 

    VISTA: A Benchmark for Spatio-Temporal Interaction Understanding in Videos

    Alejandro Aparcedo, Akash Kumar, Aaryan Garg, Dalton Pham, Wen-Kai Chen, Anirudh Bharadwaj, Aman Chadha, and Yogesh Rawat

    In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2026

    CVPRW Bib HTML Website

    @inproceedings{aparcedo2026vista,
      title = {VISTA: A Benchmark for Spatio-Temporal Interaction Understanding in Videos},
      author = {Aparcedo, Alejandro and Kumar, Akash and Garg, Aaryan and Pham, Dalton and Chen, Wen-Kai and Bharadwaj, Anirudh and Chadha, Aman and Rawat, Yogesh},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
      pages = {8411--8422},
      year = {2026},
    }

12. 

    MolSight: Molecular Property Prediction with Images

    Aaditya Baranwal, Akshaj Gupta, Yogesh S Rawat, and Shruti Vyas

    arXiv preprint arXiv:2605.10157, 2026

    arXiv Bib

    @article{baranwal2026molsight,
      title = {MolSight: Molecular Property Prediction with Images},
      author = {Baranwal, Aaditya and Gupta, Akshaj and Rawat, Yogesh S and Vyas, Shruti},
      journal = {arXiv preprint arXiv:2605.10157},
      year = {2026},
    }

2025

1. 

   MolVision: Molecular Property Prediction with Vision Language Models

   Deepan Adak, Yogesh Singh Rawat, and Shruti Vyas

   In Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2025

   NeurIPS arXiv Bib Supp Code Website

   @inproceedings{adak2025molvision,
     title = {MolVision: Molecular Property Prediction with Vision Language Models},
     author = {Adak, Deepan and Rawat, Yogesh Singh and Vyas, Shruti},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track},
     year = {2025},
   }

2. 

   Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement

   Priyank Pathak and Yogesh S. Rawat

   In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   ICCV Bib HTML PDF Video Code Poster Slides Website

   @inproceedings{pathak2025colors,
     title = {Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement},
     author = {Pathak, Priyank and Rawat, Yogesh S.},
     booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
     pages = {16797--16807},
     year = {2025},
   }

3. 

   DisenQ: Disentangling Q-Former for Activity-Biometrics

   Shehreen Azad and Yogesh Rawat

   In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   ICCV arXiv Bib Code Poster Website

   @inproceedings{azad2025disenq,
     title = {DisenQ: Disentangling Q-Former for Activity-Biometrics},
     author = {Azad, Shehreen and Rawat, Yogesh},
     booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2025},
   }

4. 

   Punching Bag vs. Punching Person: Motion Transferability in Videos

   Raiyaan Abdullah, Jared Claypoole, Michael Cogswell, Ajay Divakaran, and Yogesh Rawat

   In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   ICCV arXiv Bib HTML Code Website

   @inproceedings{abdullah2025punching,
     title = {Punching Bag vs. Punching Person: Motion Transferability in Videos},
     author = {Abdullah, Raiyaan and Claypoole, Jared and Cogswell, Michael and Divakaran, Ajay and Rawat, Yogesh},
     booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2025},
   }

5. 

   STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding

   Aaryan Garg, Akash Kumar, and Yogesh Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   CVPR arXiv Bib PDF Supp Code Website

   @inproceedings{garg2025stpro,
     title = {STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding},
     author = {Garg, Aaryan and Kumar, Akash and Rawat, Yogesh},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2025},
   }

6. 

   HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding

   Shehreen Azad, Vibhav Vineet, and Yogesh Singh Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   CVPR Bib HTML PDF Code Website

   @inproceedings{azad2025hierarq,
     title = {HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding},
     author = {Azad, Shehreen and Vineet, Vibhav and Rawat, Yogesh Singh},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {8545--8556},
     year = {2025},
   }

7. 

   DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID

   Xin Liang and Yogesh Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   CVPR Bib HTML PDF Code

   @inproceedings{liang2025differ,
     title = {DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID},
     author = {Liang, Xin and Rawat, Yogesh},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2025},
   }

8. 

   LR0.FM: Low-Resolution Zero-Shot Classification Benchmark for Foundation Models

   Priyank Pathak, Shyam Marjit, Shruti Vyas, and Yogesh S. Rawat

   In International Conference on Learning Representations (ICLR), 2025

   ICLR Bib HTML Code Poster Slides Website

   @inproceedings{pathak2025lr0fm,
     title = {LR0.FM: Low-Resolution Zero-Shot Classification Benchmark for Foundation Models},
     author = {Pathak, Priyank and Marjit, Shyam and Vyas, Shruti and Rawat, Yogesh S.},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2025},
   }

9. 

   Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

   Akash Kumar, Zsolt Kira, and Yogesh Singh Rawat

   In International Conference on Learning Representations (ICLR), 2025

   ICLR Bib HTML Supp Code Website

   @inproceedings{kumar2025cospal,
     title = {Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding},
     author = {Kumar, Akash and Kira, Zsolt and Rawat, Yogesh Singh},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2025},
   }

10. 

    T2L: Efficient Zero-Shot Action Recognition with Temporal Token Learning

    Shahzad Ahmad, Sukalpa Chanda, and Yogesh S. Rawat

    Transactions on Machine Learning Research (TMLR), 2025

    TMLR Bib HTML

    @article{ahmad2025t2l,
      title = {T2L: Efficient Zero-Shot Action Recognition with Temporal Token Learning},
      author = {Ahmad, Shahzad and Chanda, Sukalpa and Rawat, Yogesh S.},
      journal = {Transactions on Machine Learning Research (TMLR)},
      year = {2025},
    }

11. 

    Stable Mean Teacher for Semi-supervised Video Action Detection

    Akash Kumar, Sirshapan Mitra, and Yogesh Singh Rawat

    In AAAI Conference on Artificial Intelligence, 2025

    AAAI arXiv Bib Video Code Website

    @inproceedings{kumar2025stable,
      title = {Stable Mean Teacher for Semi-supervised Video Action Detection},
      author = {Kumar, Akash and Mitra, Sirshapan and Rawat, Yogesh Singh},
      booktitle = {AAAI Conference on Artificial Intelligence},
      year = {2025},
    }

12. 

    Advancing automatic photovoltaic defect detection using semi-supervised semantic segmentation of electroluminescence images

    Abhishek Jha, Yogesh Rawat, and Shruti Vyas

    Engineering Applications of Artificial Intelligence, 2025

    EAAI Bib

    @article{jha2025advancing,
      title = {Advancing automatic photovoltaic defect detection using semi-supervised semantic segmentation of electroluminescence images},
      author = {Jha, Abhishek and Rawat, Yogesh and Vyas, Shruti},
      journal = {Engineering Applications of Artificial Intelligence},
      volume = {160},
      pages = {111790},
      publisher = {Pergamon},
      year = {2025},
    }

13. 

    Understanding Depth and Height Perception in Large Visual-Language Models

    Shehreen Azad, Yash Jain, Rishit Garg, Yogesh S Rawat, and Vibhav Vineet

    In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025

    CVPRW arXiv Bib Code Website

    @inproceedings{azad2024geometer,
      title = {Understanding Depth and Height Perception in Large Visual-Language Models},
      author = {Azad, Shehreen and Jain, Yash and Garg, Rishit and Rawat, Yogesh S and Vineet, Vibhav},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
      year = {2025},
    }

14. 

    Scaling Open-Vocabulary Action Detection

    Zhen Hao Sia and Yogesh Singh Rawat

    In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

    ICCVW arXiv Bib Code Website

    @inproceedings{sia2025scaling,
      title = {Scaling Open-Vocabulary Action Detection},
      author = {Sia, Zhen Hao and Rawat, Yogesh Singh},
      booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
      pages = {6351--6361},
      year = {2025},
    }

15. 

    A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning

    Akash Kumar, Ashlesha Kumar, Vibhav Vineet, and Yogesh S Rawat

    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025

    Bib

    @inproceedings{kumar2025large,
      title = {A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning},
      author = {Kumar, Akash and Kumar, Ashlesha and Vineet, Vibhav and Rawat, Yogesh S},
      booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
      pages = {670--681},
      year = {2025},
    }

16. 

    PULSE: Physiological Understanding with Liquid Signal Extraction

    Shahzad Ahmad, Sania Bano, Sachin Verma, Yogesh Singh Rawat, Sukalpa Chanda, Santosh Kumar Vipparthi, and Subrahmanyam Murala

    In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

    WACV Bib PDF

    @inproceedings{ahmad2025pulse,
      title = {PULSE: Physiological Understanding with Liquid Signal Extraction},
      author = {Ahmad, Shahzad and Bano, Sania and Verma, Sachin and Rawat, Yogesh Singh and Chanda, Sukalpa and Vipparthi, Santosh Kumar and Murala, Subrahmanyam},
      booktitle = {2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
      pages = {4574--4584},
      year = {2025},
    }

17. 

    Coarse attribute prediction with task agnostic distillation for real world clothes changing reid

    Priyank Pathak and Yogesh S Rawat

    arXiv preprint arXiv:2505.12580, 2025

    arXiv Bib

    @article{pathak2025coarse,
      title = {Coarse attribute prediction with task agnostic distillation for real world clothes changing reid},
      author = {Pathak, Priyank and Rawat, Yogesh S},
      journal = {arXiv preprint arXiv:2505.12580},
      year = {2025},
    }

18. 

    iSafetyBench: A video-language benchmark for safety in industrial environment

    Raiyaan Abdullah, Yogesh Singh Rawat, and Shruti Vyas

    In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

    ICCVW arXiv Bib Code Website

    @inproceedings{abdullah2025isafetybench,
      title = {iSafetyBench: A video-language benchmark for safety in industrial environment},
      author = {Abdullah, Raiyaan and Rawat, Yogesh Singh and Vyas, Shruti},
      booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
      pages = {1433--1442},
      year = {2025},
    }

19. 

    Re: Verse-Can Your VLM Read a Manga?

    Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, and Shruti Vyas

    In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

    ICCVW Awarded arXiv Bib Code Website

    Best Paper Award, AI Story Workshop @ ICCV 2025

    @inproceedings{baranwal2025re,
      title = {Re: Verse-Can Your VLM Read a Manga?},
      author = {Baranwal, Aaditya and Kataria, Madhav and Agrawal, Naitik and Rawat, Yogesh S and Vyas, Shruti},
      booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
      pages = {3761--3771},
      year = {2025},
    }

20. 

    OmViD: Omni-supervised active learning for video action detection

    Aayush Rana, Akash Kumar, Vibhav Vineet, and Yogesh S Rawat

    In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

    ICCVW Bib Code

    @inproceedings{rana2025omvid,
      title = {OmViD: Omni-supervised active learning for video action detection},
      author = {Rana, Aayush and Kumar, Akash and Vineet, Vibhav and Rawat, Yogesh S},
      booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
      pages = {6911--6921},
      year = {2025},
    }

21. 

    GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis

    Sirshapan Mitra and Yogesh Singh Rawat

    In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

    ICCVW arXiv Bib Code Website

    @inproceedings{mitra2025gaitcrafter,
      title = {GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis},
      author = {Mitra, Sirshapan and Rawat, Yogesh Singh},
      booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
      pages = {3726--3735},
      year = {2025},
    }

2024

1. 

   Asynchronous Perception Machine for Efficient Test-Time-Training

   Rajat Modi and Yogesh Rawat

   In Advances in Neural Information Processing Systems (NeurIPS), 2024

   NeurIPS arXiv Bib PDF Video Blog Code Website

   @inproceedings{modi2024apm,
     title = {Asynchronous Perception Machine for Efficient Test-Time-Training},
     author = {Modi, Rajat and Rawat, Yogesh},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2024},
   }

2. 

   Navigating Hallucinations for Reasoning of Unintentional Activities

   Shresth Grover, Vibhav Vineet, and Yogesh S. Rawat

   In Findings of the Association for Computational Linguistics: EMNLP, 2024

   EMNLP Findings arXiv Bib

   @inproceedings{grover2024navigating,
     title = {Navigating Hallucinations for Reasoning of Unintentional Activities},
     author = {Grover, Shresth and Vineet, Vibhav and Rawat, Yogesh S.},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP},
     year = {2024},
   }

3. 

   Activity-Biometrics: Person Identification from Daily Activities

   Shehreen Azad and Yogesh Singh Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   CVPR arXiv Bib PDF Code

   @inproceedings{azad2024activity,
     title = {Activity-Biometrics: Person Identification from Daily Activities},
     author = {Azad, Shehreen and Rawat, Yogesh Singh},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {287--296},
     year = {2024},
   }

4. 

   Foundation models for video understanding: A survey

   Neelu Madan, Andreas Møgelmose, Rajat Modi, Yogesh S Rawat, and Thomas B Moeslund

   arXiv preprint arXiv:2405.03770, 2024

   arXiv arXiv Bib

   @article{madan2024foundation,
     title = {Foundation models for video understanding: A survey},
     author = {Madan, Neelu and M{\o}gelmose, Andreas and Modi, Rajat and Rawat, Yogesh S and Moeslund, Thomas B},
     journal = {arXiv preprint arXiv:2405.03770},
     year = {2024},
   }

5. 

   Probing conceptual understanding of large visual-language models

   Madeline Schiappa, Raiyaan Abdullah, Shehreen Azad, Jared Claypoole, Michael Cogswell, Ajay Divakaran, and Yogesh Rawat

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024

   CVPRW arXiv Bib

   @inproceedings{schiappa2024probing,
     title = {Probing conceptual understanding of large visual-language models},
     author = {Schiappa, Madeline and Abdullah, Raiyaan and Azad, Shehreen and Claypoole, Jared and Cogswell, Michael and Divakaran, Ajay and Rawat, Yogesh},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
     pages = {1797--1807},
     year = {2024},
   }

6. 

   Robustness analysis on foundational segmentation models

   Madeline Chantry Schiappa, Shehreen Azad, Sachidanand Vs, Yunhao Ge, Ondrej Miksik, Yogesh S Rawat, and Vibhav Vineet

   In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024

   CVPRW Bib

   @inproceedings{schiappa2024robustness,
     title = {Robustness analysis on foundational segmentation models},
     author = {Schiappa, Madeline Chantry and Azad, Shehreen and Vs, Sachidanand and Ge, Yunhao and Miksik, Ondrej and Rawat, Yogesh S and Vineet, Vibhav},
     booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
     pages = {1786--1796},
     year = {2024},
   }

7. 

   Semi-supervised active learning for video action detection

   Ayush Singh, Aayush J Rana, Akash Kumar, Shruti Vyas, and Yogesh Singh Rawat

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2024

   AAAI Bib PDF Code

   @inproceedings{singh2024semi,
     title = {Semi-supervised active learning for video action detection},
     author = {Singh, Ayush and Rana, Aayush J and Kumar, Akash and Vyas, Shruti and Rawat, Yogesh Singh},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {38},
     number = {5},
     pages = {4891--4899},
     year = {2024},
   }

8. 

   AirSketch: Generative Motion to Sketch

   Hui Xian Grace Lim, Xuanming Cui, Ser-Nam Lim, and Yogesh S Rawat

   In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

   NeurIPS Bib

   @inproceedings{lim2024airsketch,
     title = {AirSketch: Generative Motion to Sketch},
     author = {Lim, Hui Xian Grace and Cui, Xuanming and Lim, Ser-Nam and Rawat, Yogesh S},
     booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
     year = {2024},
   }

2023

1. 

   Self-supervised learning for videos: A survey

   Madeline C Schiappa, Yogesh S Rawat, and Mubarak Shah

   ACM Computing Surveys, 2023

   CSUR Bib PDF Code

   @article{schiappa2023self,
     title = {Self-supervised learning for videos: A survey},
     author = {Schiappa, Madeline C and Rawat, Yogesh S and Shah, Mubarak},
     journal = {ACM Computing Surveys},
     volume = {55},
     number = {13s},
     pages = {1--37},
     year = {2023},
     publisher = {ACM New York, NY},
   }

2. 

   A large-scale robustness analysis of video action recognition models

   Madeline Chantry Schiappa, Naman Biyani, Prudvi Kamtam, Shruti Vyas, Hamid Palangi, Vibhav Vineet, and Yogesh S Rawat

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

   CVPR Bib Code

   @inproceedings{schiappa2023large,
     title = {A large-scale robustness analysis of video action recognition models},
     author = {Schiappa, Madeline Chantry and Biyani, Naman and Kamtam, Prudvi and Vyas, Shruti and Palangi, Hamid and Vineet, Vibhav and Rawat, Yogesh S},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {14698--14708},
     year = {2023},
   }

3. 

   Hybrid active learning via deep clustering for video action detection

   Aayush J Rana and Yogesh S Rawat

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

   Bib PDF Code

   @inproceedings{rana2023hybrid,
     title = {Hybrid active learning via deep clustering for video action detection},
     author = {Rana, Aayush J and Rawat, Yogesh S},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {18867--18877},
     year = {2023},
   }

4. 

   Efficiently robustify pre-trained models

   Nishant Jain, Harkirat Behl, Yogesh Singh Rawat, and Vibhav Vineet

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

   Bib

   @inproceedings{jain2023efficiently,
     title = {Efficiently robustify pre-trained models},
     author = {Jain, Nishant and Behl, Harkirat and Rawat, Yogesh Singh and Vineet, Vibhav},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     pages = {5505--5515},
     year = {2023},
   }

5. 

   PRAT: PRofiling Adversarial aTtacks

   Rahul Ambati, Naveed Akhtar, Ajmal Mian, and Yogesh S Rawat

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

   Bib

   @inproceedings{ambati2023prat,
     title = {PRAT: PRofiling Adversarial aTtacks},
     author = {Ambati, Rahul and Akhtar, Naveed and Mian, Ajmal and Rawat, Yogesh S},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     pages = {3667--3676},
     year = {2023},
   }

6. 

   On occlusions in video action detection: Benchmark datasets and training recipes

   Rajat Modi, Vibhav Vineet, and Yogesh Rawat

   Advances in Neural Information Processing Systems, 2023

   NeurIPS Bib HTML Code

   @article{modi2023occlusions,
     title = {On occlusions in video action detection: Benchmark datasets and training recipes},
     author = {Modi, Rajat and Vineet, Vibhav and Rawat, Yogesh},
     journal = {Advances in Neural Information Processing Systems},
     volume = {36},
     pages = {57306--57335},
     year = {2023},
   }

7. 

   Revealing the unseen: Benchmarking video action recognition under occlusion

   Shresth Grover, Vibhav Vineet, and Yogesh Rawat

   Advances in Neural Information Processing Systems, 2023

   NeurIPS Bib HTML Website

   @article{grover2023revealing,
     title = {Revealing the unseen: Benchmarking video action recognition under occlusion},
     author = {Grover, Shresth and Vineet, Vibhav and Rawat, Yogesh},
     journal = {Advances in Neural Information Processing Systems},
     volume = {36},
     pages = {65642--65664},
     year = {2023},
   }

8. 

   EZ-CLIP: Efficient Zero-shot Video Action Recognition

   Shahzad Ahmad, Sukalpa Chanda, and Yogesh S Rawat

   arXiv preprint arXiv:2312.08010, 2023

   arXiv Bib PDF Code

   @article{ahmad2023ez,
     title = {EZ-CLIP: Efficient Zero-shot Video Action Recognition},
     author = {Ahmad, Shahzad and Chanda, Sukalpa and Rawat, Yogesh S},
     journal = {arXiv preprint arXiv:2312.08010},
     year = {2023},
   }

2022

1. 

   GabriellaV2: Towards better generalization in surveillance videos for action detection

   Ishan Dave, Zacchaeus Scheffer, Akash Kumar, Sarah Shiraz, Yogesh Singh Rawat, and Mubarak Shah

   In IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2022

   WACV Bib PDF Website

   @inproceedings{dave2022gabriellav2,
     title = {GabriellaV2: Towards better generalization in surveillance videos for action detection},
     author = {Dave, Ishan and Scheffer, Zacchaeus and Kumar, Akash and Shiraz, Sarah and Rawat, Yogesh Singh and Shah, Mubarak},
     booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)},
     pages = {122--132},
     year = {2022},
   }

2. 

   End-to-End Semi-Supervised Learning for Video Action Detection

   Akash Kumar and Yogesh Singh Rawat

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2022

   CVPR Bib

   @inproceedings{kumar2022end,
     title = {End-to-End Semi-Supervised Learning for Video Action Detection},
     author = {Kumar, Akash and Rawat, Yogesh Singh},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
     year = {2022},
   }

3. 

   Don’t Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation

   Ziwei Xu, Yogesh S Rawat, Yongkang Wong, Mohan Kankanhalli, and Mubarak Shah

   In Advances in Neural Information Processing Systems, 2022

   NeurIPS Bib HTML Code

   @inproceedings{xu2022don,
     title = {Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation},
     author = {Xu, Ziwei and Rawat, Yogesh S and Wong, Yongkang and Kankanhalli, Mohan and Shah, Mubarak},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2022},
   }

4. 

   Robustness analysis of video-language models against visual and language perturbations

   Madeline Schiappa, Shruti Vyas, Hamid Palangi, Yogesh Rawat, and Vibhav Vineet

   Advances in Neural Information Processing Systems, 2022

   NeurIPS Bib PDF Website

   @article{schiappa2022robustness,
     title = {Robustness analysis of video-language models against visual and language perturbations},
     author = {Schiappa, Madeline and Vyas, Shruti and Palangi, Hamid and Rawat, Yogesh and Vineet, Vibhav},
     journal = {Advances in Neural Information Processing Systems},
     volume = {35},
     pages = {34405--34420},
     year = {2022},
   }

5. 

   Svgraph: Learning semantic graphs from instructional videos

   Madeline C Schiappa and Yogesh S Rawat

   2022 IEEE Eighth International Conference on Multimedia Big Data (BigMM), 2022

   BigMM Bib

   @article{schiappa2022svgraph,
     title = {Svgraph: Learning semantic graphs from instructional videos},
     author = {Schiappa, Madeline C and Rawat, Yogesh S},
     journal = {2022 IEEE Eighth International Conference on Multimedia Big Data (BigMM)},
     pages = {45--52},
     year = {2022},
   }

6. 

   Are all Frames Equal? Active Sparse Labeling for Video Action Detection

   Aayush Rana and Yogesh S Rawat

   In Advances in Neural Information Processing Systems, 2022

   NeurIPS Bib HTML Code

   @inproceedings{rana2022all,
     title = {Are all Frames Equal? Active Sparse Labeling for Video Action Detection},
     author = {Rana, Aayush and Rawat, Yogesh S},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2022},
   }

7. 

   Video Action Detection: Analysing Limitations and Challenges

   Rajat Modi, Aayush Jung Rana, Akash Kumar, Praveen Tirupattur, Shruti Vyas, Yogesh Singh Rawat, and Mubarak Shah

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

   Bib PDF Website

   @inproceedings{modi2022video,
     title = {Video Action Detection: Analysing Limitations and Challenges},
     author = {Modi, Rajat and Rana, Aayush Jung and Kumar, Akash and Tirupattur, Praveen and Vyas, Shruti and Rawat, Yogesh Singh and Shah, Mubarak},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
     year = {2022},
   }

2021

1. 

   In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning

   Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, and Mubarak Shah

   In The International Conference on Learning Representations (ICLR), 2021

   ICLR Bib PDF Video Code

   @inproceedings{rizve2021defense,
     title = {In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning},
     author = {Rizve, Mamshad Nayeem and Duarte, Kevin and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {The International Conference on Learning Representations (ICLR)},
     year = {2021},
   }

2. 

   Modeling Multi-Label Action Dependencies for Temporal Action Localization

   Praveen Tirupattur, Kevin Duarte, Yogesh Rawat, and Mubarak Shah

   In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

   CVPR Bib PDF Code

   @inproceedings{tirupattur2021modeling,
     title = {Modeling Multi-Label Action Dependencies for Temporal Action Localization},
     author = {Tirupattur, Praveen and Duarte, Kevin and Rawat, Yogesh and Shah, Mubarak},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
     year = {2021},
   }

3. 

   We Don’t Need Thousand Proposals: Single Shot Actor-Action Detection in Videos

   Aayush J Rana and Yogesh S Rawat

   In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021

   WACV Bib PDF Code Website

   @inproceedings{rana2021we,
     title = {We Don't Need Thousand Proposals: Single Shot Actor-Action Detection in Videos},
     author = {Rana, Aayush J and Rawat, Yogesh S},
     booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
     pages = {2960--2969},
     year = {2021},
   }

4. 

   Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities

   Sirnam Swetha, Hilde Kuehne, Yogesh S Rawat, and Mubarak Shah

   In 2021 IEEE International Conference on Image Processing, 2021

   ICIP Bib

   @inproceedings{swetha2021unsupervised,
     title = {Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities},
     author = {Swetha, Sirnam and Kuehne, Hilde and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {2021 IEEE International Conference on Image Processing},
     year = {2021},
   }

5. 

   Plm: Partial label masking for imbalanced multi-label classification

   Kevin Duarte, Yogesh Rawat, and Mubarak Shah

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021

   Bib

   @inproceedings{duarte2021plm,
     title = {Plm: Partial label masking for imbalanced multi-label classification},
     author = {Duarte, Kevin and Rawat, Yogesh and Shah, Mubarak},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {2739--2748},
     year = {2021},
   }

6. 

   Novel View Video Prediction Using a Dual Representation

   Sarah Shiraz, Krishna Regmi, Shruti Vyas, Yogesh S Rawat, and Mubarak Shah

   In IEEE International Conference on Image Processing, 2021

   ICIP Bib

   @inproceedings{shiraz2021novel,
     title = {Novel View Video Prediction Using a Dual Representation},
     author = {Shiraz, Sarah and Regmi, Krishna and Vyas, Shruti and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {IEEE International Conference on Image Processing},
     year = {2021},
   }

7. 

   Tinyaction challenge: Recognizing real-world low-resolution activities in videos

   Praveen Tirupattur, Aayush J Rana, Tushar Sangam, Shruti Vyas, Yogesh S Rawat, and Mubarak Shah

   arXiv preprint arXiv:2107.11494, 2021

   arXiv Bib

   @article{tirupattur2021tinyaction,
     title = {Tinyaction challenge: Recognizing real-world low-resolution activities in videos},
     author = {Tirupattur, Praveen and Rana, Aayush J and Sangam, Tushar and Vyas, Shruti and Rawat, Yogesh S and Shah, Mubarak},
     journal = {arXiv preprint arXiv:2107.11494},
     year = {2021},
   }

8. 

   NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels

   Mohit Sharma, Raj Patra, Harshal Desai, Shruti Vyas, Yogesh Rawat, and Rajiv Ratn Shah

   In ACM International Conference on Multimedia in Asia, 2021

   MMAsia Bib PDF Website

   @inproceedings{sharma2021noisyactions2m,
     title = {NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels},
     author = {Sharma, Mohit and Patra, Raj and Desai, Harshal and Vyas, Shruti and Rawat, Yogesh and Shah, Rajiv Ratn},
     booktitle = {ACM International Conference on Multimedia in Asia},
     year = {2021},
   }

9. 

   Pose-guided Generative Adversarial Net for Novel View Action Synthesis

   Xianhang Li, Junhao Zhang, Kunchang Li, Shruti Vyas, and Yogesh S Rawat

   In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021

   Bib PDF Code Website

   @inproceedings{li2021pose,
     title = {Pose-guided Generative Adversarial Net for Novel View Action Synthesis},
     author = {Li, Xianhang and Zhang, Junhao and Li, Kunchang and Vyas, Shruti and Rawat, Yogesh S},
     booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
     year = {2021},
   }

10. 

    "Knights": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021

    Ishan Dave, Naman Biyani, Brandon Clark, Rohit Gupta, Yogesh Rawat, and Mubarak Shah

    arXiv preprint arXiv:2110.07758, 2021

    arXiv Bib

    @article{dave2021knights,
      title = {"Knights": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021},
      author = {Dave, Ishan and Biyani, Naman and Clark, Brandon and Gupta, Rohit and Rawat, Yogesh and Shah, Mubarak},
      journal = {arXiv preprint arXiv:2110.07758},
      year = {2021},
    }

11. 

    LARNet: Latent Action Representation for Human Action Synthesis

    Naman Biyani, Aayush J Rana, Shruti Vyas, and Yogesh S Rawat

    In The British Machine Vision Conference (BMVC), 2021

    BMVC Bib PDF Code Slides Website

    @inproceedings{biyani2021larnet,
      title = {LARNet: Latent Action Representation for Human Action Synthesis},
      author = {Biyani, Naman and Rana, Aayush J and Vyas, Shruti and Rawat, Yogesh S},
      booktitle = {The British Machine Vision Conference (BMVC)},
      year = {2021},
    }

12. 

    Reformulating zero-shot action recognition for multi-label actions

    Alec Kerrigan, Kevin Duarte, Yogesh Rawat, and Mubarak Shah

    Advances in Neural Information Processing Systems, 2021

    NeurIPS Bib PDF Slides

    @article{kerrigan2021reformulating,
      title = {Reformulating zero-shot action recognition for multi-label actions},
      author = {Kerrigan, Alec and Duarte, Kevin and Rawat, Yogesh and Shah, Mubarak},
      journal = {Advances in Neural Information Processing Systems},
      volume = {34},
      pages = {25566--25577},
      year = {2021},
    }

2020

1. 

   Multi-view Action Recognition using Cross-view Video Prediction

   Shruti Vyas, Yogesh S Rawat, and Mubarak Shah

   In European Conference on Computer Vision (ECCV), 2020

   ECCV Bib Code

   @inproceedings{vyas2020multi,
     title = {Multi-view Action Recognition using Cross-view Video Prediction},
     author = {Vyas, Shruti and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2020},
   }

2. 

   TinyVIRAT: Low-resolution Video Action Recognition

   Ugur Demir, Yogesh S Rawat, and Mubarak Shah

   In 25th International Conference on Pattern Recognition (ICPR), 2020

   ICPR arXiv Bib Website

   @inproceedings{demir2020tinyvirat,
     title = {TinyVIRAT: Low-resolution Video Action Recognition},
     author = {Demir, Ugur and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {25th International Conference on Pattern Recognition (ICPR)},
     year = {2020},
   }

3. 

   Adversarial Learning for Personalized Tag Recommendation

   Erik Quintanilla, Yogesh Rawat, Andrey Sakryukin, Mubarak Shah, and Mohan Kankanhalli

   IEEE Transactions on Multimedia, 2020

   TMM Bib

   @article{quintanilla2020adversarial,
     title = {Adversarial Learning for Personalized Tag Recommendation},
     author = {Quintanilla, Erik and Rawat, Yogesh and Sakryukin, Andrey and Shah, Mubarak and Kankanhalli, Mohan},
     journal = {IEEE Transactions on Multimedia},
     year = {2020},
   }

4. 

   Visual-textual Capsule Routing for Text-based Video Segmentation

   Bruce McIntosh, Kevin Duarte, Yogesh S Rawat, and Mubarak Shah

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

   CVPR Bib PDF

   @inproceedings{mcintosh2020visual,
     title = {Visual-textual Capsule Routing for Text-based Video Segmentation},
     author = {McIntosh, Bruce and Duarte, Kevin and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {9942--9951},
     year = {2020},
   }

5. 

   Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos

   Mamshad Nayeem Rizve, Ugur Demir, Praveen Tirupattur, Aayush Jung Rana, Kevin Duarte, Ishan Dave, Yogesh Singh Rawat, and Mubarak Shah

   In 25th International Conference on Pattern Recognition (ICPR), 2020

   ICPR Awarded Bib PDF Video Website

   Best Scientific Paper Award, ICPR 2020

   @inproceedings{rizve2020gabriella,
     title = {Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos},
     author = {Rizve, Mamshad Nayeem and Demir, Ugur and Tirupattur, Praveen and Rana, Aayush Jung and Duarte, Kevin and Dave, Ishan and Rawat, Yogesh Singh and Shah, Mubarak},
     booktitle = {25th International Conference on Pattern Recognition (ICPR)},
     pages = {4237--4244},
     year = {2020},
   }

6. 

   A Recurrent Transformer Network for Novel View Action Synthesis

   Kara Marie Schatz, Erik Quintanilla, Shruti Vyas, and Yogesh S Rawat

   In Proceedings of the European Conference on Computer Vision (ECCV), 2020

   ECCV Bib

   @inproceedings{schatz2020recurrent,
     title = {A Recurrent Transformer Network for Novel View Action Synthesis},
     author = {Schatz, Kara Marie and Quintanilla, Erik and Vyas, Shruti and Rawat, Yogesh S},
     booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
     year = {2020},
   }

7. 

   View-invariant action recognition

   Yogesh S Rawat and Shruti Vyas

   In Computer Vision: A Reference Guide, 2020

   Book Chapter

   Bib

   @incollection{rawat2020view,
     title = {View-invariant action recognition},
     author = {Rawat, Yogesh S and Vyas, Shruti},
     booktitle = {Computer Vision: A Reference Guide},
     publisher = {Springer, Cham},
     year = {2020},
   }

2019

1. 

   CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing

   Kevin Duarte, Yogesh S Rawat, and Mubarak Shah

   In Proceedings of the IEEE International Conference on Computer Vision, 2019

   ICCV Bib

   @inproceedings{duarte2019capsulevos,
     title = {CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing},
     author = {Duarte, Kevin and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
     year = {2019},
   }

2. 

   Photography and exploration of tourist locations based on optimal foraging theory

   Yogesh Singh Rawat, Mubarak Shah, and Mohan S Kankanhalli

   IEEE Transactions on Circuits and Systems for Video Technology, 2019

   TCSVT Bib

   @article{rawat2019photography,
     title = {Photography and exploration of tourist locations based on optimal foraging theory},
     author = {Rawat, Yogesh Singh and Shah, Mubarak and Kankanhalli, Mohan S},
     journal = {IEEE Transactions on Circuits and Systems for Video Technology},
     volume = {30},
     number = {7},
     pages = {2276--2287},
     publisher = {IEEE},
     year = {2019},
   }

2018

1. 

   VideoCapsuleNet: A Simplified Network for Action Detection

   Kevin Duarte, Yogesh S Rawat, and Mubarak Shah

   In Advances in Neural Information Processing Systems, 2018

   NeurIPS Bib

   @inproceedings{duarte2018videocapsulenet,
     title = {VideoCapsuleNet: A Simplified Network for Action Detection},
     author = {Duarte, Kevin and Rawat, Yogesh S and Shah, Mubarak},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2018},
   }

2. 

   ThoughtViz: Visualizing Human Thoughts Using Generative Adversarial Network

   Praveen Tirupattur, Yogesh Singh Rawat, Concetto Spampinato, and Mubarak Shah

   In Proceedings of the 2018 ACM on Multimedia Conference, 2018

   ACM MM Bib

   @inproceedings{tirupattur2018thoughtviz,
     title = {ThoughtViz: Visualizing Human Thoughts Using Generative Adversarial Network},
     author = {Tirupattur, Praveen and Rawat, Yogesh Singh and Spampinato, Concetto and Shah, Mubarak},
     booktitle = {Proceedings of the 2018 ACM on Multimedia Conference},
     pages = {950--958},
     year = {2018},
     organization = {ACM},
   }

3. 

   Time-aware and view-aware video rendering for unsupervised representation learning

   Shruti Vyas, Yogesh S Rawat, and Mubarak Shah

   arXiv preprint arXiv:1811.10699, 2018

   arXiv Bib

   @article{vyas2018time,
     title = {Time-aware and view-aware video rendering for unsupervised representation learning},
     author = {Vyas, Shruti and Rawat, Yogesh S and Shah, Mubarak},
     journal = {arXiv preprint arXiv:1811.10699},
     year = {2018},
   }

2017

1. 

   A spring-electric graph model for socialized group photography

   Yogesh Singh Rawat, Mingli Song, and Mohan S Kankanhalli

   IEEE Transactions on Multimedia, 2017

   TMM Bib

   @article{rawat2017spring,
     title = {A spring-electric graph model for socialized group photography},
     author = {Rawat, Yogesh Singh and Song, Mingli and Kankanhalli, Mohan S},
     journal = {IEEE Transactions on Multimedia},
     volume = {20},
     number = {3},
     pages = {754--766},
     publisher = {IEEE},
     year = {2017},
   }

2016

1. 

   ConTagNet: Exploiting user context for image tag recommendation

   Yogesh Singh Rawat and Mohan S Kankanhalli

   In Proceedings of the 24th ACM international conference on Multimedia, 2016

   ACM MM Bib

   @inproceedings{rawat2016contagnet,
     title = {ConTagNet: Exploiting user context for image tag recommendation},
     author = {Rawat, Yogesh Singh and Kankanhalli, Mohan S},
     booktitle = {Proceedings of the 24th ACM international conference on Multimedia},
     pages = {1102--1106},
     year = {2016},
   }

2. 

   ClickSmart: A Context-Aware Viewpoint Recommendation System for Mobile Photography

   Yogesh Rawat and Mohan Kankanhalli

   2016

   TCSVT Bib

   @article{rawat2016clicksmart,
     title = {ClickSmart: A Context-Aware Viewpoint Recommendation System for Mobile Photography},
     author = {Rawat, Yogesh and Kankanhalli, Mohan},
     year = {2016},
     publisher = {IEEE Transactions on Circuits and Systems for Video Technology},
   }

3. 

   Real Time Assistance in Photography Using Social Media

   YOGESH SINGH RAWAT

   National University of Singapore, 2016

   Bib

   @phdthesis{rawat2016real,
     title = {Real Time Assistance in Photography Using Social Media},
     author = {RAWAT, YOGESH SINGH},
     school = {National University of Singapore},
     year = {2016},
   }

2015

1. 

   Context-aware photography learning for smart mobile devices

   Yogesh Singh Rawat and Mohan S Kankanhalli

   ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2015

   TOMM Bib

   @article{rawat2015context,
     title = {Context-aware photography learning for smart mobile devices},
     author = {Rawat, Yogesh Singh and Kankanhalli, Mohan S},
     journal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)},
     volume = {12},
     number = {1s},
     pages = {1--24},
     year = {2015},
     publisher = {ACM New York, NY, USA},
   }

2. 

   Real-time assistance in multimedia capture using social media

   Yogesh Singh Rawat

   In Proceedings of the 23rd ACM international conference on Multimedia, 2015

   ACM MM Bib

   @inproceedings{rawat2015real,
     title = {Real-time assistance in multimedia capture using social media},
     author = {Rawat, Yogesh Singh},
     booktitle = {Proceedings of the 23rd ACM international conference on Multimedia},
     pages = {641--644},
     year = {2015},
   }

2014

1. 

   Context-based photography learning using crowdsourced images and social media

   Yogesh Singh Rawat and Mohan S Kankanhalli

   In Proceedings of the 22nd ACM international conference on Multimedia, 2014

   ACM MM Bib

   @inproceedings{rawat2014context,
     title = {Context-based photography learning using crowdsourced images and social media},
     author = {Rawat, Yogesh Singh and Kankanhalli, Mohan S},
     booktitle = {Proceedings of the 22nd ACM international conference on Multimedia},
     pages = {217--220},
     year = {2014},
   }

2. 

   Mode of teaching based segmentation and annotation of video lectures

   Yogesh Singh Rawat, Chidansh Bhatt, and Mohan S Kankanhalli

   In 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI), 2014

   CBMI Bib

   @inproceedings{rawat2014mode,
     title = {Mode of teaching based segmentation and annotation of video lectures},
     author = {Rawat, Yogesh Singh and Bhatt, Chidansh and Kankanhalli, Mohan S},
     booktitle = {2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI)},
     pages = {1--4},
     organization = {IEEE},
     year = {2014},
   }

2008

1. 

   An analytic scheme for online handwritten Bangla cursive word recognition

   U Bhattacharya, A Nigam, YS Rawat, and SK Parui

   Proc. of the 11th ICFHR, 2008

   ICFHR Bib

   @article{bhattacharya2008analytic,
     title = {An analytic scheme for online handwritten Bangla cursive word recognition},
     author = {Bhattacharya, U and Nigam, A and Rawat, YS and Parui, SK},
     journal = {Proc. of the 11th ICFHR},
     pages = {320--325},
     year = {2008},
   }