Learning to recognize objects in egocentric activities

By Alireza Fathi, Xiaofeng Ren, James M. Rehg. 2011

633 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

Segment Anything (2023, background): “ADE20K[117] BBBC038v1[12] Cityscapes[25] DOORS[80] DRAM[24] EgoHOS[113] GTEA[34,63] Hypersim[86] IBD[17] iShape[111] LVIS[44] NDD20[100] NDISPark[22,23] OVIS[81] PPDLS[74] Plittersdorf[46] STREETS[91] TimberSeg[38] TrashCan[52] VISOR[28,27] WoodScape[112] PIDRay[104] ZeroWaste-f[6] Figure 8: Samples”
Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, neutral): “[10] further separates hand and interacting object from the whole foreground by assuming a color histogram prior over hand super-pixels, and uses graph-cut to segment hands and objects.”
Temporal Convolutional Networks for Action Segmentation and Detection (2016, methodology): “We use MERL Shopping which was designed for action detection, Georgia Tech Egocentric Activities which was designed for action segmentation, and 50 Salads which has been used for both.”
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.”
KrishnaCam: Using a longitudinal, single-person, egocentric dataset for scene understanding tasks (2016, background): “The two peaks of the graph (steep rises in the amount of novel visual data) correspond to days the student spent outside his home city.”
Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection (2020, methodology): “Before the revolution of deep convolutional networks in the field of computer vision, [30, 15, 34] proposed motion-based approaches for binary foreground segmentation with the assumption that the motion pattern is different for the foreground and background.”
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities (2022, methodology): “Temporal action segmentation datasets like GTEA [12] and 50Salads [47] are small-scale datasets (28 and 50 videos v7 v1 v3 v5 v8 v4 v2 e1 e4 e2 e3 Figure 2.”
Action recognition in RGB-D egocentric videos (2017, background): “For these reasons, increasing works have been proposed to investigate the egocentric videos from different aspects, like video summarization [15–17], visual recognition [18–21], social interaction [22], gaze detection [23] and many others.”
Pixel-Level Hand Detection in Ego-centric Videos (2013, methodology): “Baseline: Video stabilization+gPb+superpixel+graphcut [6]”
EgoVQA - An Egocentric Video Question Answering Benchmark Dataset (2019, background): “Recent computer vision research topics on studying first-person videos have included object detection [19,24,25,39], hands detection [10], scene understanding [26], activity recognition [23, 47], person identification and segmentation [20, 40, 57, 58], gaze detection and tracking [34, 62], etc.”
SAM 2: Segment Anything in Images and Videos (2024, neutral): “…et al., 2016), BBBC038v1 (Caicedo et al., 2019), DOORS (Pugliatti & Topputo, 2022), DRAM (Cohen et al., 2022), EgoHOS (Zhang et al., 2022), GTEA (Fathi et al., 2011; Li et al., 2015), iShape (Yang et al., 2021a), NDD20 (Trotter et al., 2020), NDISPark (Ciampi et al., 2021, 2022), OVIS (Qi et…”
Multi-Stream Deep Neural Networks for RGB-D Egocentric Action Recognition (2019, background): “tion [4]–[6], person re-identification [7] and gaze analysis [8].”
Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals (2017, background): “0 40 640×480 Head X - - Kitchen Activity GTEA [21] 4 28 0.”
Understanding egocentric activities (2011, methodology): “We use semi-supervised learning framework from [7] to build object classifiers given these weak informations.”
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, background): “Other datasets exist, but they are mostly provided to support specific findings and thus are either limited in terms of total number of frames, [8,21,25,47], or do not exhibit a sufficient variety in terms of content [1, 4, 5, 15, 17, 20, 41, 46].”
A Survey on Activity Detection and Classification Using Wearable Sensors (2017, background): “[113] similarly classify the type of interaction multiple subjects are involved in, such as”
Video-Based Human Behavior Understanding: A Survey (2013, methodology): “[125] use an egocentric approach, where video captured from a wearable camera is used to view the scene in front of the user at all times.”
Summarization of Egocentric Videos: A Comprehensive Survey (2017, methodology): “of datasets such as the following: CMU-MMAC [51], recorded in a staged kitchen; GTEA [52] and GTEA-gaze [50], which contain very specific videos, sometimes staged and short; UEC”
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping (2019, methodology): “Occlusion images are randomly sampled from the EgoHands [30], GTEA Hand2K [31, 32, 33] and object renderings from ShapeNet [34].”