24 citations · 27 across the 10 of their papers we have counts for
10 papers
Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Model
James Thiering, Tarun Sethupat Radha Krishna, Dylan Zelkin +1
With the rise of online and virtual learning, monitoring and enhancing student engagement have become an important aspect of effective education. Traditional methods of assessing a…
Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
Ayush K. Rai, Kyle Min, Tarun Krishna +3
Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using…
An accurate detection is not all you need to combat label noise in web-noisy datasets
Paul Albert, Jack Valmadre, Eric Arazo +3
Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical obse…
Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach
Ayush K. Rai, Tarun Krishna, Feiyan Hu +4
Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos w…
Discrepancies of subtrees
Tarun Krishna, Peleg Michaeli, Michail Sarantis +2
We study multicolour, oriented and high-dimensional discrepancies of the set of all subtrees of a tree. As our main result, we show that the -colour discrepancy of the subtrees…
Unifying Synergies between Self-supervised Learning and Dynamic Computation
Tarun Krishna, Ayush K Rai, Alexandru Drimbarean +5
Computationally expensive training strategies make self-supervised learning (SSL) impractical for resource constrained industrial settings. Techniques like knowledge distillation (…
Motion Aware Self-Supervision for Generic Event Boundary Detection
Ayush K. Rai, Tarun Krishna, Julia Dietlmeier +3
The task of Generic Event Boundary Detection (GEBD) aims to detect moments in videos that are naturally perceived by humans as generic and taxonomy-free event boundaries. Modeling…
Dynamic Channel Selection in Self-Supervised Learning
Tarun Krishna, Ayush K. Rai, Yasser A. D. Djilali +3
Whilst computer vision models built using self-supervised approaches are now commonplace, some important questions remain. Do self-supervised models learn highly redundant channel…
Discerning Generic Event Boundaries in Long-Form Wild Videos
Ayush K Rai, Tarun Krishna, Julia Dietlmeier +3
Detecting generic, taxonomy-free event boundaries invideos represents a major stride forward towards holisticvideo understanding. In this paper we present a technique forgeneric ev…
Evaluating Contrastive Models for Instance-based Image Retrieval
Tarun Krishna, Kevin McGuinness, Noel O'Connor
In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discrimi…