Year-2022

 

Recent Submissions

  • Extreme abstractive text summarization 
    Simran; Chakraborty, Tanmoy (Advisor); Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2022-12)
    Extreme Abstractive Summarization of long scientific papers requires domain knowledge and a concise summary maintaining faithfulness to the source and covering novel aspects presented in the paper. Human annotations are ...
  • Sarcasm explanation in multimodal dialogues 
    Vaibhav, Shashwat; Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2022-12)
    Sarcasm is a means to convey ridicule or contempt. There has been a plethora of work in sentiment analysis, of which sarcasm is one of the most challenging tasks due to the incongruity between the surface level and the ...
  • Microservice-based in-network AES solution for FPGA NICs 
    Hussain, Lasani (IIIT-Delhi, 2022-12)
    Data centers demand high throughput (100 to 400 Gbps) and sub-millisecond latency. The performance of data center applications heavily depends on the efficiency of the underlying TCP stack. Despite several optimizations, ...
  • Knowledge graph assisted extreme summarization of scientific documents in hyperbolic space 
    Mukherjee, Asmita; Chakraborty, Tanmoy (Advisor); Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2022-12)
    A research paper is a document that presents an original work and introduces new concepts and makes interconnections between them via arguments and statements. Extreme Summarization involves high compression of the information ...
  • Unsupervised meta generative object re-identification 
    Giri, Biman; Subramanyam, A V (Advisor) (IIIT-Delhi, 2022-05)
    Unsupervised domain adaptation severely suffers from huge domain gap in fine grained recognition tasks such as vehicle re-identification (re-id). Existing works either focus on fully unsupervised methods using tracklet or ...
  • On the implementation of internet censorship in India 
    Singh, Kartikey; Chakravarty, Sambuddho (Advisor) (IIIT-Delhi, 2022-07)
    In this work we highlight the evolution of Internet censorship within the largest democracy i.e., India. We first report a new form of Internet censorship i.e., mobile app blocking and describe in detail the mechanics ...
  • Dolphin : a cellular voice based internet shutdown resistance system 
    Sharma, Rishi; Chakravarty, Sambuddho (Advisor); Maity, Mukulika (Advisor) (IIIT-Delhi, 2022-07)
    Traditional censorship revolves around blocking access to some websites (or services) over the Internet. However, recently there has been a rise in the events of an extreme form of censorship viz., deliberate Internet ...
  • TamilNLP: low resource language processing 
    Singh, Himanshu; Shah, Rajiv Ratn (Advisor) (IIIT-Delhi, 2022-07)
    In this paper, we worked on different aspects like dataset, annotation guidelines, annotation platform, and models to build a complete eco-system, aimed at making significant contributions towards NLP for the Tamil language. ...
  • Exploiting the tradeoff between energy consumption and execution time in mixed cpu-gpu edge-cloud environment 
    Rathee, Ravi; Bhattacharya, Arani (Advisor) (IIIT-Delhi, 2022-06)
    Mobile devices like smartphones can augment their low-power processors by offloading GPU- heavy applications to cloud servers. However, cloud data centers consume a lot of energy and have high latency. To mitigate the ...
  • Detection of doctored speech : towards an end-to-end parametric learn-able filter approach 
    Arora, Rohit; Anand, Saket (Advisor); Mohan, Aanchan (Advisor) (IIIT-Delhi, 2022-05)
    The Automatic Speaker Verification (ASV) systems have potential in biomet- rics applications for logical control access and authentication. A lot of things happen to be at stake if the ASV system is compromised. The questions ...
  • User-centric power optimization in smart home environments 
    Gupta, Saurabh; Buduru, Arun Balaji (Advisor); Kumaraguru, Ponnurangam (Advisor) (IIIT-Delhi, 2022-07)
    Rapid advancements in the Internet of Things (IoT) have facilitated efficient de- ployments of smart environment solutions for specific user requirements. With the increase in the number of IoT devices, it has become ...
  • Information extraction in user's complaints 
    T G, Narayanan; Akhtar, Md. Shad (Advisor) (IIITD, 2022-08)
    The task of Named Entity Recognition is one of the most explored fields in the Natural Language Processing domain. Numerous existing works have tried to uncover different aspects of this common yet unique field. The NER ...
  • A comprehensive understanding of code-mixed language semantics using hierarchical transformer 
    S, Tharun; Akhtar, Md. Shad (Advisor); Chakraborty, Tanmoy (Advisor) (IIIT-Delhi, 2022-05)
    Being a popular mode of text-based communication in multilingual communities, code-mixing in online social media has became an important subject to study. Learn- ing the semantics and morphology of code-mixed language ...