Presently, I am a faculty in the Department of Computer Science & Engineering  (CSE) at Indian Institute of Technology, Jodhpur (IITJ), India. 

Previously, I was an INSPIRE Faculty Fellow at Indian Institute of Science, Bengaluru, India. 

Before that, I completed my BTech and PhD from IIIT-Hyderabad, India. 

CV

Note: Due to time constraints, I won't be able to accept any application for internship/short-term engagement. 

Email: yashaswi@iitj.ac.in 

Address: 

Room No. 227, Department of Computer Science and Engineering, 

Indian Institute of Technology Jodhpur, 

NH 62, Nagaur Road, Karwar, 

Jodhpur, Rajasthan (India) - 342030. 

Contact: (91) (291) 280 1260

Note: The following articles (and associated data/codes) are made available under the Creative Commons CC-BY-NC- ND license.

Journal Publications: 

• "Early-stage autism diagnosis using action videos and contrastive feature learning" [code] [link] [view] [pdf] 

In: Multimedia Systems 2023 (Asha Rani, Pankaj Yadav and Yashaswi Verma) 

• "A retrieval-based approach for diverse and image-specific adversary selection" [link] [pdf] 

      In: IJMIR 2020 (Rajvardhan Singh Ravat and Yashaswi Verma) 

• "Diverse Image Annotation with Missing Labels" [code] [link] [pdf] 

       In: PR 2019 (Yashaswi Verma) 

• "Automatic image annotation: The quirks and what works" [code] [link] [pdf] 

      In: MTA 2018 (Ayushi Dutta, Yashaswi Verma and C. V. Jawahar) 

• "Cross-specificity: Modelling data semantics for cross-modal matching and retrieval" [link] [pdf] 

       In: IJMIR 2018 (Yashaswi Verma, Abhishek Jha and C. V. Jawahar) 

• "Image Annotation by Propagating Labels from Semantic Neighbourhoods" [code] [link] [pdf] 

       In: IJCV 2017 (Yashaswi Verma and C. V. Jawahar) 

• "A Support Vector Approach for Cross-Modal Search of Images and Texts" [code] [link] [pdf] 

       In: CVIU 2017 (Yashaswi Verma and C. V. Jawahar) 

Conference/Workshop Publications: 

• "Cross-modal Retrieval Using Contrastive Learning of Visual-Semantic Embeddings" [code] [link] [arXiv] 

In: ICPR 2022 (Anurag Jain and Yashaswi Verma) 

• "Surprising Effectiveness of Random Feature Embeddings in eXtreme Classification" [code] [link] [arXiv] 

In: ICPR 2022 (Yashaswi Verma) 

• "Multi-view Multi-label Canonical Correlation Analysis for Cross-modal Matching and Retrieval" [code] [link] [pdf] 

In CVPR Workshop 2022 (Rushil Sanghavi and Yashaswi Verma) 

• "Worst Case Adversarial Perturbation and Effect of Feature Normalization on Max-Margin Multi-label Classifiers" [pdf] 

In: ICVGIP Workshop 2021 (Ritesh Kumar Gupta and Yashaswi Verma) 

• "Recurrent Image Annotation With Explicit Inter-Label Dependencies" [code] [link] [pdf] 

       In: ECCV 2020 (Ayushi Dutta, Yashaswi Verma and C. V. Jawahar) 

• "A Robust Distance with Correlated Metric Learning for Multi-Instance Multi-Label Data" [link] [pdf] 

       In: ACM Multimedia 2016 (Yashaswi Verma and C. V. Jawahar) 

• "A Probabilistic Approach for Image Retrieval Using Descriptive Textual Queries" [link] [pdf] 

       In: ACM Multimedia 2015 (Yashaswi Verma and C. V. Jawahar) 

• "Exploring Locally Rigid Discriminative Patches for Learning Relative Attributes" [project] [code] [link] [pdf] 

       In: BMVC 2015 (Yashaswi Verma and C. V. Jawahar)

• "Im2Text and Text2Im: Associating Images and Texts for Cross-Modal Retrieval" [code] [link] [pdf] 

       In: BMVC 2014 (Yashaswi Verma and C. V. Jawahar) 

• "Relative Parts: Distinctive Parts for Learning Relative Attributes" [project] [code] [link] [pdf] 

       In: CVPR 2014 (Ramachandruni N. Sandeep, Yashaswi Verma and C. V. Jawahar) 

• "Exploring SVM for Image Annotation in Presence of Confusing Labels" [link] [pdf] 

       In: BMVC 2013 (Yashaswi Verma and C. V. Jawahar) 

• "Generating Image Descriptions Using Semantic Similarities in the Output Space" [link] [pdf] 

       In: CVPR Workshop 2013 (Yashaswi Verma, Ankush Gupta, Prashanth Mannem and C. V. Jawahar) 

• "Neti Neti: In Search of Deity" [link] [pdf] 

       In: ICVGIP 2012 (Yashaswi Verma and C. V. Jawahar) 

• "Image Annotation Using Metric Learning in Semantic Neighbourhoods" [code] [link] [pdf] 

       In: ECCV 2012 (Yashaswi Verma and C. V. Jawahar) 

• "Choosing Linguistics over Vision to Describe Images" [link] [pdf] 

       In: AAAI 2012 (Ankush Gupta, Yashaswi Verma and C. V. Jawahar)

PhD dissertation: 

"Understanding Semantic Association Between Images and Text" [pdf] 

Panel of Examiners: Dr. Manish Gupta, Dr. Raghavan Manmatha, Dr. Rajeev Rastogi and Prof. C. V. Jawahar