Detecting activities of daily living in first-person camera views

By Hamed Pirsiavash, Deva Ramanan. 2012

789 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Joint Discovery of Object States and Manipulation Actions (2017, background): “Modeling co-occurrences of objects and actions have shown benefits for recognizing actions in [11, 19, 26, 35, 47].”
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, background): “2011; Ryoo and Matthies 2013) as well as features from human gaze, hands, and objects (Spriggs, De La Torre, and Hebert 2009; Lee, Ghosh, and Grauman 2012; Fathi, Farhadi, and Rehg 2011; Pirsiavash and Ramanan 2012; Li and Kitani 2013; Lee and Grauman 2015).”
Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, neutral): “Most relevant to our work are those containing unscripted daily life activity, which includes EPIC-Kitchens [43,44], UT Ego [129,210], Activities of Daily Living (ADL) [179], and the Disney dataset [66].”
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding (2016, methodology): “For example, the Activities of Daily Living dataset [25] recorded 20 people performing unscripted, everyday activities in their homes in first person, and another extended that idea to animals [26].”
Wanderlust: Online Continual Object Detection in the Real World (2021, background): “[23] extend the evaluation from static images to video snippets like Activity Daily Living (ADL) [33] dataset and YouTube Objects (YTO) datasets [34] for incremental domain adaptation.”
Learning human activities and object affordances from RGB-D videos (2012, background): “Some recent works (Gupta et al., 2009; Yao and Fei-Fei, 2010; Aksoy et al., 2010; Jiang et al., 2011a; Pirsiavash and Ramanan, 2012) show that modeling the interaction between human poses and objects in 2D videos results in a better performance on the tasks of object detection and activity recogniti”
Simitate: A Hybrid Imitation Learning Benchmark (2019, neutral): “Pirsiavash et al. [31] created a ﬁrst person dataset containing images from people fulﬁlling daily activity tasks.”
Scaling Egocentric Vision: The EPIC-KITCHENS Dataset (2018, methodology): “3: Instructions used to collect video narrations from our participants it has 11.5M frames vs 1M in ADL, 90x more annotated action segments, and 4x more object bounding boxes, making it the largest ﬁrst-person dataset to date.”
Moments in Time Dataset: One Million Videos for Event Understanding (2018, background): “[14] and ADL [35] uses daily human activities to collect data with natural spatio-temporal context.”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “There has been a significant amount of work in detecting human activities from 2D RGB videos [1], [2], [3], from inertial/location sensors [4], and more recently from RGB-D videos [5], [6], [7].”
Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos (2018, background): “In fact, our dataset is one of the largest first-person datasets available [2, 4, 6, 1], has significantly more diversity (112 actors in many rooms), and most importantly, is the only large-scale dataset to offer pairs of first and third-person views that we can learn from.”
From Lifestyle Vlogs to Everyday Interactions (2017, background): “We compare sample frames from our dataset in comparison with video-collection-by-acting efforts such as [35, 23, 8, 28].”
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video (2020, methodology): “…action recognition such as the use of multiple modalities for video analysis [23], the use of Temporal Segment Networks [27] as a principled way to train CNNs for action recognition, as well as the explicit encoding of object-based features [36], [38], [41], [43], [45] to analyze egocentric video.”
Anticipating the future by watching unlabeled video (2015, methodology): “We validate our approach on forecasting actions and objects on two challenging inthe-wild datasets of human actions in television shows [26] and egocentric videos for activities of daily living [30].”
Understanding Hand-Object Manipulation with Grasp Types and Object Attributes (2016, background): “The work in [25] has shown that recognizing handled objects helps to infer daily hand activities.”
What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention (2019, methodology): “Specifically, we build on previous ideas investigated in the context of action recognition such as the use of multiple modalities for video analysis [49], the use of Temporal Segment Networks [61] as a principled way to train CNNs for action recognition, as well as the explicit encoding of object-ba”
Predicting Important Objects for Egocentric Video Summarization (2015, methodology): “Recent methods explore activity recognition [34,35,12,36], handled object recognition [37], novelty detection [38], hand detection [39], gaze prediction [40], social interaction analysis [41], or activity discovery for nonvisual sensory data [42].”