{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1910.01279","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","created":"2019-10-03","cited_by_count":582},{"id":"1610.09585","title":"Conditional Image Synthesis With Auxiliary Classifier GANs","created":"2016-10-30","cited_by_count":565},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"1604.00825","title":"Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers","created":"2016-04-04","cited_by_count":199},{"id":"1605.09304","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","created":"2016-05-30","cited_by_count":181},{"id":"1506.02753","title":"Inverting Visual Representations with Convolutional Networks","created":"2015-06-09","cited_by_count":170},{"id":"2103.16372","title":"Source-Free Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":168},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"1602.03616","title":"Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks","created":"2016-02-11","cited_by_count":106},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102},{"id":"1512.02017","title":"Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images","created":"2015-12-07","cited_by_count":93},{"id":"2203.11894","title":"GradViT: Gradient Inversion of Vision Transformers","created":"2022-03-22","cited_by_count":53},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36},{"id":"2302.04869","title":"Reversible Vision Transformers","created":"2023-02-09","cited_by_count":33},{"id":"2010.12697","title":"Investigating Saturation Effects in Integrated Gradients","created":"2020-10-23","cited_by_count":22},{"id":"1902.01078","title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","created":"2019-02-04","cited_by_count":20},{"id":"2201.12961","title":"Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations","created":"2022-01-31","cited_by_count":18},{"id":"2109.14274","title":"Designing Counterfactual Generators using Deep Model Inversion","created":"2021-09-29","cited_by_count":15},{"id":"1909.08611","title":"Class Feature Pyramids for Video Explanation","created":"2019-09-18","cited_by_count":8},{"id":"2005.11394","title":"MANGO: A Python Library for Parallel Hyperparameter Tuning","created":"2020-05-22","cited_by_count":8},{"id":"2001.11366","title":"Black-Box Saliency Map Generation Using Bayesian Optimisation","created":"2020-01-30","cited_by_count":3},{"id":"2101.12447","title":"The Mind's Eye: Visualizing Class-Agnostic Features of CNNs","created":"2021-01-29","cited_by_count":2},{"id":"2210.17130","title":"BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models","created":"2022-10-31","cited_by_count":1}],"next_cursor":null}