Publications

For an updated list of publications please refer to my Google Scholar profile. * denotes equal contribution

	Inductive Biases For Higher-Order Visual Cognition Shashank Shekhar Master's Thesis, 2022 paper / We demonstrated state-of-the-art results in generating scene graphs from natural images by using a sequential subject->predicate->object generation using a transformer encoder on object bounding boxes derived using a detection model.
	Neural response time analysis: Explainable artificial intelligence using only a stopwatch Eric Taylor*, Shashank Shekhar* , Graham W Taylor Applied AI Letters, 2021 paper / video / We extended our work on Neural Response Time analysis from CVPR-W 2020 with an additional experiment showing that NRTs are sensitive to intra-class variations, yet can be used to reliably inform between intra-class variations between objects.
	Context-aware Scene Graph Generation with Seq2Seq Transformers Yichao Lu, Himanshu Rai, Jason Chang, Boris Knyazev, Guangwei Yu, Shashank Shekhar , Graham W. Taylor, Maksims Volkovs International Conference on Computer Vision, 2021 paper / code / We demonstrated state-of-the-art results in generating scene graphs from natural images by using a sequential subject->predicate->object generation using a transformer encoder on object bounding boxes derived using a detection model.
	Response Time Analysis for Explainability of Visual Processing in CNNs Eric Taylor*, Shashank Shekhar* , Graham W Taylor Computer Vision and Pattern Recognition (CVPR) Workshop, 2020 paper / video / We adapt response time evaluation in human psychophysics for deep learning to calculate Neural Response Times (NRT) by profiling dynamic DNNs. We verify that NRT is able to corroborate known effects about the feature space composed by object recognition models when tested on OOD view points. We further demonstrate that NRT can be used to causally verify Scene Grammar effects in identifying semantic and syntactic inconsistencies across visual scenes.
	Operator-in-the-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification KL Navaneet, Ravi Kiran Sarvadevabhatla, Shashank Shekhar , R Venkatesh Babu, Anirban Chakraborty IEEE Transactions on Information Forensics and Security, 2019 paper / We developed a human-in-the-loop system to rank image retrieval results from an image recognition CNN and then merge them with human choice for person re-identification. Our method showed consistent improvement in performance across 6 cameras compared to only relying on model insights.
	From Strings to Things: Knowledge-enabled VQA Model that can Read and Reason Ajeet Kumar Singh, Anand Mishra, Shashank Shekhar, Anirban Chakraborty International Conference on Computer Vision, 2019 paper / website / We released the first dataset for Visual Question Answering (VQA) that requires traversing an external knowledge-graph as well as understanding scene-text through Optical Character Recognition (OCR). We also proposed a Graph-RNN based approach for VQA with external knowledge and demonstrated state-of-the-art results.
	OCR-VQA: Visual question answering by reading text in images Anand Mishra, Shashank Shekhar , Ajeet Kumar Singh, Anirban Chakraborty International Conference on Document Analysis and Recognition, 2019 paper / website / We released the first dataset for Visual Question Answering that requires understanding scene-text through Optical Character Recognition (OCR).
	Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN Janpreet Singh*, Shashank Shekhar* IEEE BigData Cup 2018 workshop, 2018 paper / code / We fine-tuned a Mask R-CNN trained on MS-COCO dataset to detect and classify road damage in real-world images of roads taken from smartphones.