{"list":"other","total":85,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"1711.09325","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","created":"2017-11-26","cited_by_count":389},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"1901.11448","title":"Feature-Critic Networks for Heterogeneous Domain Generalization","created":"2019-01-31","cited_by_count":130},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"1912.00381","title":"Gate-Shift Networks for Video Action Recognition","created":"2019-12-01","cited_by_count":76},{"id":"2009.05769","title":"Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning","created":"2020-09-12","cited_by_count":66},{"id":"2108.02432","title":"Token Shift Transformer for Video Classification","created":"2021-08-05","cited_by_count":61},{"id":"2211.06612","title":"Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning","created":"2022-11-12","cited_by_count":53},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49},{"id":"2108.05137","title":"Zero-Shot Day-Night Domain Adaptation with a Physics Prior","created":"2021-08-11","cited_by_count":47},{"id":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47},{"id":"2001.06499","title":"Temporal Interlacing Network","created":"2020-01-17","cited_by_count":45},{"id":"2304.03709","title":"Meta-causal Learning for Single Domain Generalization","created":"2023-04-07","cited_by_count":43},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35},{"id":"2304.00424","title":"Progressive Random Convolutions for Single Domain Generalization","created":"2023-04-02","cited_by_count":34},{"id":"2002.07442","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","created":"2020-02-18","cited_by_count":33},{"id":"2107.04932","title":"Aligning Correlation Information for Domain Adaptation in Action Recognition","created":"2021-07-11","cited_by_count":30},{"id":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","cited_by_count":29},{"id":"2007.15829","title":"Adversarial Bipartite Graph Learning for Video Domain Adaptation","created":"2020-07-31","cited_by_count":28},{"id":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27},{"id":"2106.01603","title":"CT-Net: Channel Tensorization Network for Video Classification","created":"2021-06-03","cited_by_count":26},{"id":"2303.02328","title":"Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalization","created":"2023-03-04","cited_by_count":26},{"id":"2203.16195","title":"On the Road to Online Adaptation for Semantic Image Segmentation","created":"2022-03-30","cited_by_count":23},{"id":"2205.14467","title":"Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors","created":"2022-05-28","cited_by_count":19},{"id":"1912.03716","title":"VideoDG: Generalizing Temporal Relations in Videos to Novel Domains","created":"2019-12-08","cited_by_count":14},{"id":"2108.09976","title":"Revealing the Distributional Vulnerability of Discriminators by Implicit Generators","created":"2021-08-23","cited_by_count":10},{"id":"2005.02113","title":"Adaptive Interaction Modeling via Graph Operations Search","created":"2020-05-05","cited_by_count":5},{"id":"2303.02693","title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","created":"2023-03-05","cited_by_count":5},{"id":"2206.09380","title":"Supervision Adaptation Balancing In-distribution Generalization and Out-of-distribution Detection","created":"2022-06-19","cited_by_count":4},{"id":"2206.09387","title":"Dual Representation Learning for Out-of-Distribution Detection","created":"2022-06-19","cited_by_count":4}],"next_cursor":null}