# Delta Sampling R-BERT for limited data and low-light action recognition Source: [Delta Sampling R-BERT for limited data and low-light action recognition]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:22:37.170Z Authors: Sanchit Hira, Ritwik Das, Abhinav Modi, Daniil Pakhomov Published: 2021-07-12T05:35:51.000Z ## Abstract We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset. Most previous works only evaluate performance on large, well illuminated datasets like Kinetics and HMDB51. We demonstrate that our work is able to achieve a very low error rate while being trained on a much smaller dataset of dark videos. We also explore a variety of training and inference strategies including domain transfer methodologies and also propose a simple but useful frame selection strategy. Our empirical results demonstrate that we beat previously published baseline models by 11%. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()