74 citations · 135 across the 18 of their papers we have counts for
16 papers · 1 filter
Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering
Nidhi Hegde, Sujoy Paul, Gagan Madan +1
Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) t…
Is it an i or an l: Test-time Adaptation of Text Line Recognition Models
Debapriya Tula, Sujoy Paul, Gagan Madan +3
Recognizing text lines from images is a challenging problem, especially for handwritten documents due to large variations in writing styles. While text line recognition models are…
Weakly supervised information extraction from inscrutable handwritten document images
Sujoy Paul, Gagan Madan, Akankshya Mishra +3
State-of-the-art information extraction methods are limited by OCR errors. They work well for printed text in form-like documents, but unstructured, handwritten documents still rem…
Novel Class Discovery without Forgetting
K J Joseph, Sujoy Paul, Gaurav Aggarwal +4
Humans possess an innate ability to identify and differentiate instances that they are not familiar with, by leveraging and adapting the knowledge that they have acquired so far. I…
Spacing Loss for Discovering Novel Categories
K J Joseph, Sujoy Paul, Gaurav Aggarwal +4
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances fro…
Test-time Adaptation with Slot-Centric Models
Mihir Prabhudesai, Anirudh Goyal, Sujoy Paul +6
Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time ada…
Unsupervised Adaptation of Semantic Segmentation Models without Source Data
Sujoy Paul, Ansh Khurana, Gaurav Aggarwal
We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims t…
SITA: Single Image Test-time Adaptation
Ansh Khurana, Sujoy Paul, Piyush Rai +2
In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially,…
Reconstruction guided Meta-learning for Few Shot Open Set Recognition
Sayak Nag, Dripta S. Raychaudhuri, Sujoy Paul +1
In many applications, we are constrained to learn classifiers from very limited data (few-shot classification). The task becomes even more challenging if it is also required to ide…
Adversarial Knowledge Transfer from Unlabeled Data
Akash Gupta, Rameswar Panda, Sujoy Paul +2
While machine learning approaches to visual recognition offer great promise, most of the existing methods rely heavily on the availability of large quantities of labeled training d…
Domain Adaptive Semantic Segmentation Using Weak Labels
Sujoy Paul, Yi-Hsuan Tsai, Samuel Schulter +2
Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired t…
Learning Person Re-identification Models from Videos with Weak Supervision
Xueping Wang, Sujoy Paul, Dripta S. Raychaudhuri +3
Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled da…
Context-Aware Query Selection for Active Learning in Event Recognition
Mahmudul Hasan, Sujoy Paul, Anastasios I. Mourikis +1
Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g.,…
Weakly Supervised Video Moment Retrieval From Text Queries
Niluthpol Chowdhury Mithun, Sujoy Paul, Amit K. Roy-Chowdhury
There have been a few recent methods proposed in text to video moment retrieval using natural language queries, but requiring full supervision during training. However, acquiring a…
Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning
Sujoy Paul, Sourya Roy, Amit K. Roy-Chowdhury
Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantia…
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Sujoy Paul, Sourya Roy, Amit K Roy-Chowdhury
Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards redu…