AND T

By MD YOSHIO KINAMI, I. Miyazaki, Mdi

How researchers see this paper

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

In Software Engineering

Citations in the corpus

Evaluating the Social Impact of Generative AI Systems in Systems and Society (2023, background): “There is no “view from nowhere”; in evaluating anything, a particular frame of reference [207] is imposed [237].”
A Note on Data Biases in Generative Models (2020, background): “Datasets are not the sole cause of societal bias in ML models [16].”
Generative Image Modeling Using Spatial LSTMs (2015, methodology): “Spatial LSTMs were implemented using the Caffe framework [17].”
Return of the Devil in the Details: Delving Deep into Convolutional Nets (2014, methodology): “The second modification is the use of spatially-extended local descriptors [26] instead of a spatial pyramid.”
AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions (2017, methodology): “We employ two methods: the dense optical flow estimation method TVL-1 [27], and a CNNbased iterative Deep Flow model which is a variant of the FlowNet-ss network [17].”
Adversarial Training and Robustness for Multiple Perturbations (2019, background): “We follow a line of works that study distributions for which adversarial examples exist unconditionally [41, 21, 33, 12, 14, 26].”
On Safeguarding Privacy and Security in the Framework of Federated Learning (2019, background): “• Dummy: The concept of dummy method stems from location privacy protection [11].”
A Causal Bayesian Networks Viewpoint on Fairness (2018, background): “In response, Equivant published a technical report [20] refuting the claims of bias made by ProPublica and concluded that COMPAS is sufficiently calibrated, in the sense that it satisfies predictive parity at key thresholds.”
Class-Incremental Continual Learning Into the eXtended DER-Verse (2022, positive): “In more detail, we always use Stochastic Gradient Descent as optimizer and a number of epochs that varies according to the dataset (50 for CIFAR-100, 80 for miniImageNet and 70 for NTU); in line with [11], [31], [41], we also define a set of epochs at which the learning rate is divided by 10 ([35, 4”
Differential Recurrent Neural Networks for Action Recognition (2015, background): “In many recent works, the LSTMs have shown tremendous potential in action recognition tasks [ 1][11][6].”
Action recognition with trajectory-pooled deep-convolutional descriptors (2015, methodology): “In order to verify the effectiveness of TDDs, we conduct experiments on two public large datasets, namely HMDB51 [15] and UCF101 [ 26].”
Hierarchical Surface Prediction for 3D Object Reconstruction (2017, background): “The benefits of using a coarse-to-fine approach in learning based optical flow prediction has also recently been pointed out [26], [15].”
Accelerating Very Deep Convolutional Networks for Classification and Detection (2015, methodology): “The very deep VGG models [1] have substantially 679 improved a wide range of visual recognition tasks, 680 including object detection [9], [2], [10], [11], semantic 681 segmentation [12], [13], [14], [40], [41], image cap- 682 tioning [42], [43], [44], video/action recognition [45], 683 image questi”
Continuous Doubly Constrained Batch Reinforcement Learning (2021, neutral): “In practice, it is difficult to know which technique will perform best, unless one can do proper offline policy evaluation (OPE) of different candidate policies before their actual online deployment [15, 45].”
Information Dropout: Learning Optimal Representations Through Noisy Computation (2016, background): “Some have focused on creating representations that are maximally invariant to nuisances, especially when they have the structure of a (possibly infinite-dimensional) group acting on the data, like [12], or, when the nuisance is a locally compact group acting on each layer, by successive approximatio”
Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm (2013, methodology): “The randomizedKaczmarz method[36, 6, 14, 20, 38, 7, 37, 12, 41, 21] for solving the least squares problem (5.”
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey (2018, methodology): “5: Top-row: Example of changing a facial attribute ‘wearing lipstick’ to ‘not wearing lipstick’ by Fast Flipping Attribute method [130].”
More than a million ways to be pushed. A high-fidelity experimental dataset of planar pushing (2016, methodology): “More recently, data-driven models [17, 7, 18, 19, 20] have been proposed as an alternative approach to analysis.”
Designing an encoder for StyleGAN image manipulation (2021, background): “Last, [24, 40] have considered the so called Style Space, and are able to identify specific components that have a clear effect on spatial regions or on a single attribute.”