KrishnaCam: Using a longitudinal, single-person, egocentric dataset for scene understanding tasks

By Krishna Kumar Singh, Kayvon Fatahalian, Alexei A. Efros. 2016

73 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, neutral): “[205] Krishna Kumar Singh, Kayvon Fatahalian, and Alexei A Efros.”
From Recognition to Cognition: Visual Commonsense Reasoning (2018, neutral): “Commonsense Reasoning Our task unifies work involving reasoning about commonsense phenomena, such as physics [54, 84], social interactions [2, 77, 12, 27], procedure understanding [91, 3] and predicting what might happen next in a video [74, 17, 92, 78, 18, 64, 85].”
The Challenges of Continuous Self-Supervised Learning (2022, methodology): “The second data stream is composed by consecutive frames from the KrishnaCAM dataset(4) [74] which records egocentric videos spanning nine months in the life of a computer vision graduate student.”
Wanderlust: Online Continual Object Detection in the Real World (2021, methodology): “We sample 80 videos from KrishnaCam, which uniformly span in time.”
From Lifestyle Vlogs to Everyday Interactions (2017, background): “While egocentric/life-logging efforts like [37, 30, 8, 28] do offer ways to obtain large amounts of data in terms of volume, achieving diversity and coverage is an open challenge.”
Leveraging Uncertainty to Rethink Loss Functions and Evaluation Measures for Egocentric Action Anticipation (2018, background): “Previous works investigated different egocentric anticipation tasks [39, 26, 29, 24, 28, 37, 7, 11, 4, 25].”
Egocentric Future Localization (2016, background): “Notably, the relationship between visual semantics and egomotion has been recently studied [1, 14, 37].”
Deepdiary: Lifelogging image captioning and summarization (2018, unknown): “An alternative is to use unsupervised techniques that do not try to recognize speci ﬁ c content, but instead look for recurring visual patterns that may correspond to important content [57,81], or choose key images to summarize video or photo streams [62,73,90].”
What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention (2019, background): “Anticipation in First Person Vision Past works on anticipation from egocentric visual data have investigated different problems and considered different evaluation frameworks [5, 10, 17, 42, 45, 47, 50, 53, 65, 68].”
Predicting the Future from First Person (Egocentric) Vision: A Survey (2021, background): “KrishnaCam [66]: The largest dataset of egocentric videos for person’s trajectory path forecasting.”
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (2023, unknown): “…interest in egocentric video understanding, facilitated by recent ego-video datasets showing unscripted daily-life activity as in Ego4D [47], EPIC-Kitchens [27, 28, 163], UT Ego [78], ADL [119], and KrishnaCam [147], or procedural activities as in EGTea [81], AssistQ [172], Meccano [126],…”