Recognizing linked events: Searching the space of feasible explanations

By Dima Damen, David C. Hogg. 2009

2,123 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition, Natural Language Processing

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 Automotive Engineering

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016, methodology): “Similarly, region graphs and scene graphs have been shown to improve semantic image retrieval (Johnson et al., 2015, Schuster et al., 2015).”
Movie Description (2016, methodology): “…label semantics. b) Training one-vs-all SVMs for speciﬁc label groups consistently improves the performance as it avoids “wrong” negatives. c) Focusing on namely TACoS Multi-Level (Rohrbach et al. 2014), and showed the comparable performance to manually annotated SRs, see (Rohrbach et al. 2015c).”
Evolving Robust Neural Architectures to Defend from Adversarial Attacks (2019, background): “Universal perturbation types of attacks were shown possible in which a single perturbation added to most of the samples is capable of fooling a neural network in most of the cases [MoosaviDezfooli et al., 2017].”
Conditional variance penalties and domain shift robustness (2017, background): “Deep neural networks (DNNs) have achieved outstanding performance on prediction tasks like visual object and speech recognition (Krizhevsky et al. 2012; Szegedy et al. 2015; He et al. 2015).”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “RNN-based approach Chai et al. (2016) proposed to fuse RGB and depth in a two-stream RNN (2S-RNN) for gesture recognition.”
The limits and potentials of deep learning for robotics (2018, background): “2017 saw a surge of deep learning in robotics: workshops at CVPR (3) and NIPS (87) built bridges between the robotics, computer vision, and machine learning communities.”
Cognitive Mapping and Planning for Visual Navigation (2017, methodology): “When using RGB images as input, we triangulated SIFT feature points in the RGB images (registered using the ground truth egomotion) to obtain the observed 3D points (we used the COLMAP library (Schönberger and Frahm 2016)).”
Interpolation Consistency Training for Semi-Supervised Learning (2019, methodology): “While [Zhang et al., 2018; Tokozume et al., 2018] was proposed to perform interpolations in the input space, [Verma et al.”
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning (2020, methodology): “As any machine learning model is trained on a ﬁnite dataset, and the imaginable set of unknown unknowns is inﬁnite, we refer to the challenge of recognizing the latter as open set recognition in analogy to prior works (Scheirer et al., 2013, 2014; Bendale and Boult, 2015, 2016; Boult et al., 2019).”
Learning SO(3) Equivariant Representations with Spherical CNNs (2017, background): “Gens and Domingos (2014) produce maps of finite-multiparameter groups, Zhou et al. (2017) and Marcos et al. (2016) use a rotational filter orbit to produce oriented feature maps and rotationally invariant features, and Lenc and Vedaldi (2015) propose a transformation layer which acts as a…”
Robust Lasso With Missing and Grossly Corrupted Observations (2011, methodology): “We establish conditions for the design matrix such that the solution of the extended Lasso has the exact signed supports.”
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks (2018, methodology): “…neural networks, e.g., more complex modern convolutional neural network (CNN) architectures such as VGGNet (He et al., 2016), ResNet (He et al., 2016), Wide ResNet (Zagoruyko and Komodakis, 2016), DenseNet (Huang et al., 2017), training with Adam or its variants typically…”
Inductive Bias of Deep Convolutional Networks through Pooling Geometry (2016, background): “…the fact that convolutional arithmetic circuits are equivalent to SimNets, a new deep learning architecture that has recently demonstrated promising empirical performance ([5, 7]), we focus in this paper on convolutional arithmetic circuits as representatives of the class of convolutional networks.”
Convolutional Networks with Adaptive Inference Graphs (2017, background): “Recently, similar approaches have been proposed for neural networks (Li et al. 2015; Yang et al. 2016).”
Super-Resolution with Deep Convolutional Sufficient Statistics (2015, background): “Parametric models with sparse regularization have enjoyed great success in this problem (Elad & Aharon (2006); Yang et al. (2008)), thanks to their capacity to capture local regularity with efﬁcient convex optimization methods (Mairal et al. (2009)).”