Understanding egocentric activities

By Alireza Fathi, Ali Farhadi, James M. Rehg. 2011

414 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, background): “, optical flows) [98, 99] as well as features from human gaze, hands, and objects [100, 101, 102, 103, 104, 105].”
Delving into Egocentric Actions (2015, neutral): “In contrast, state-of-the-art egocentric action recognition methods [6] [27] [7] rely mainly on an object-centric representation for discriminating action categories.”
Temporal Convolutional Networks for Action Segmentation and Detection (2016, methodology): “In the literature, our task goes by the name action segmentation [7, 8, 6, 15, 29, 16, 10] or action detection [28, 20, 21, 25].”
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.”
Next-active-object prediction from egocentric videos (2017, background): “[15] proposed to analyze egocentric activities to jointly infer activities, hands and objects.”
Egocentric Hand Track and Object-Based Human Action Recognition (2019, background): “In recent years the egocentric point of view has been employed by the research community to address computer vision challenges such as activity recognition [1] and object detection [2] traditionally contemplated as belonging in the domain of third-person vision.”
H2O: Two Hands Manipulating Objects for First Person Interaction Recognition (2021, background): “It is also common to extract features with CNNs and leverage additional 2D cues related to motion, hand location, object location or object class, in isolation [3, 46, 53] or jointly [19, 21, 25, 67, 74].”
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations (2017, background): “role of hands while manipulating objects has attracted the interest from both computer vision and robotics communities. From an action recognition perspective and only using RGB cues, recent research [5,13,14,31,44,56] has delved into recognizing daily actions and determined that both manipulated ob”
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”
Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video (2017, background): “Egocentric videos, also referred to as ﬁrst-person videos, have been frequently advocated to provide a unique perspective into object interactions [12, 5, 19].”
Social interactions: A first-person perspective (2012, background): “In our previous work [8, 9] we recognize daily activities such as meal preparation.”
Learning to Predict Gaze in Egocentric Video (2013, background): “[6] proposed to model object, action and activity jointly in egocentric vision.”
Understanding Hand-Object Manipulation with Grasp Types and Object Attributes (2016, methodology): “[8, 9] used appearance around the regions of hand-object interactions to recognize egocentric actions.”
The Open World of Micro-Videos (2016, background): “Wearable cameras such as Google Glass and GoPro have spurred interest in analyzing egocentric views [18,19,20,21].”
Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video (2016, background): “Egocentric activity analysis Most recent egocentric vision work studies activity recognition [14, 17, 21, 22, 23, 24, 15] or object recognition [20, 13].”
Who Let the Dogs Out? Modeling Dog Behavior from Visual Data (2018, background): “, [7, 32, 18, 19]) since we study the dog’s behavior from the perspective of the dog.”
This Hand Is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video (2014, background): “In fact, most work in egocentric activity recognition assumes that activities can be characterized by the in-hand manipulation of certain objects [7, 19].”
Multi-modal Egocentric Activity Recognition using Audio-Visual Features (2018, background): “detection of cheese and bread objects imply “making cheese sandwich” activity) [7].”
H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions (2019, background): “[12, 14] use motion cues to segment hands and objects, and then extract features from these foreground regions.”
Predicting Important Objects for Egocentric Video Summarization (2015, background): “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 non-visual sensory data [42].”