Search Results for author: Israat Haque

Found 4 papers, 0 papers with code

Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics

no code implementations22 Jul 2023 Quazi Mishkatul Alam, Israat Haque, Nael Abu-Ghazaleh

In this paper, we introduce LtC, a collaborative framework between the video source and the analytics server, that efficiently learns to reduce the video streams within an analytics pipeline.

Video Compression

Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking

no code implementations16 Feb 2023 Zichong Wang, Yang Zhou, Meikang Qiu, Israat Haque, Laura Brown, Yi He, Jianwu Wang, David Lo, Wenbin Zhang

The increasing use of Machine Learning (ML) software can lead to unfair and unethical decisions, thus fairness bugs in software are becoming a growing concern.

Benchmarking counterfactual +1

Preventing Discriminatory Decision-making in Evolving Data Streams

no code implementations16 Feb 2023 Zichong Wang, Nripsuta Saxena, Tongjia Yu, Sneha Karki, Tyler Zetty, Israat Haque, Shan Zhou, Dukka Kc, Ian Stockwell, Albert Bifet, Wenbin Zhang

However, most fair machine learning (fair-ML) work to address bias in decision-making systems has focused solely on the offline setting.

Decision Making Fairness

Attention Mechanism based Cognition-level Scene Understanding

no code implementations17 Apr 2022 Xuejiao Tang, Tai Le Quy, Eirini Ntoutsi, Kea Turner, Vasile Palade, Israat Haque, Peng Xu, Chris Brown, Wenbin Zhang

Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world.

Question Answering Scene Understanding +2

Cannot find the paper you are looking for? You can Submit a new open access paper.