{"list":"other","total":51,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"id":"2007.13916","title":"Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases","created":"2020-07-28","cited_by_count":143},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2010.16219","title":"HOI Analysis: Integrating and Decomposing Human-Object Interaction","created":"2020-10-30","cited_by_count":81},{"id":"2109.08203","title":"Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision","created":"2021-09-16","cited_by_count":81},{"id":"2006.00626","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","created":"2020-05-31","cited_by_count":69},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1804.10851","title":"Imbalanced Deep Learning by Minority Class Incremental Rectification","created":"2018-04-28","cited_by_count":65},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41},{"id":"2010.09676","title":"Detecting Hands and Recognizing Physical Contact in the Wild","created":"2020-10-19","cited_by_count":38},{"id":"1708.02901","title":"Transitive Invariance for Self-supervised Visual Representation Learning","created":"2017-08-09","cited_by_count":37},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35},{"id":"1807.11794","title":"Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition","created":"2018-07-31","cited_by_count":28},{"id":"2002.03137","title":"Symbiotic Attention with Privileged Information for Egocentric Action Recognition","created":"2020-02-08","cited_by_count":27},{"id":"2104.00616","title":"Composable Augmentation Encoding for Video Representation Learning","created":"2021-04-01","cited_by_count":13},{"id":"2007.07306","title":"COBE: Contextualized Object Embeddings from Narrated Instructional Video","created":"2020-07-14","cited_by_count":12},{"id":"2012.05689","title":"Interactive Fusion of Multi-level Features for Compositional Activity Recognition","created":"2020-12-10","cited_by_count":9}],"next_cursor":null}