{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1812.02391","title":"Meta-Transfer Learning for Few-Shot Learning","created":"2018-12-06","cited_by_count":306},{"id":"1806.00064","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","created":"2018-05-31","cited_by_count":270},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186},{"id":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"1906.05186","title":"Boosting Few-Shot Visual Learning with Self-Supervision","created":"2019-06-12","cited_by_count":140},{"id":"2204.07305","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","created":"2022-04-15","cited_by_count":126},{"id":"2104.14690","title":"Entailment as Few-Shot Learner","created":"2021-04-29","cited_by_count":123},{"id":"1705.02498","title":"A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions","created":"2017-05-06","cited_by_count":108},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92},{"id":"1903.11341","title":"Diversity with Cooperation: Ensemble Methods for Few-Shot Classification","created":"2019-03-27","cited_by_count":70},{"id":"1905.01102","title":"Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning","created":"2019-05-03","cited_by_count":69},{"id":"1711.09125","title":"Appearance-and-Relation Networks for Video Classification","created":"2017-11-24","cited_by_count":61},{"id":"1905.04398","title":"Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training","created":"2019-05-10","cited_by_count":57},{"id":"1905.11641","title":"Image Deformation Meta-Networks for One-Shot Learning","created":"2019-05-28","cited_by_count":56},{"id":"1812.09213","title":"Learning Compositional Representations for Few-Shot Recognition","created":"2018-12-21","cited_by_count":50},{"id":"1908.05257","title":"Few-Shot Learning with Global Class Representations","created":"2019-08-14","cited_by_count":44},{"id":"1704.05051","title":"Google's Cloud Vision API Is Not Robust To Noise","created":"2017-04-16","cited_by_count":37},{"id":"1706.06969","title":"Comparing deep neural networks against humans: object recognition when the signal gets weaker","created":"2017-06-21","cited_by_count":34},{"id":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28},{"id":"2109.09883","title":"On the Importance of Distractors for Few-Shot Classification","created":"2021-09-20","cited_by_count":14},{"id":"2210.04510","title":"Multi-Modal Fusion Transformer for Visual Question Answering in Remote Sensing","created":"2022-10-10","cited_by_count":13},{"id":"1709.10207","title":"Provably Minimally-Distorted Adversarial Examples","created":"2017-09-29","cited_by_count":12},{"id":"1907.03196","title":"Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition","created":"2019-07-06","cited_by_count":12},{"id":"1811.03875","title":"Multimodal One-Shot Learning of Speech and Images","created":"2018-11-09","cited_by_count":11},{"id":"2109.13576","title":"Multimodality in Meta-Learning: A Comprehensive Survey","created":"2021-09-28","cited_by_count":11},{"id":"1811.09192","title":"Self Paced Adversarial Training for Multimodal Few-shot Learning","created":"2018-11-22","cited_by_count":8},{"id":"2108.12957","title":"Searching for Two-Stream Models in Multivariate Space for Video Recognition","created":"2021-08-30","cited_by_count":4},{"id":"1806.05147","title":"Cross-modal Hallucination for Few-shot Fine-grained Recognition","created":"2018-06-13","cited_by_count":3},{"id":"2210.13188","title":"Dissecting Deep Metric Learning Losses for Image-Text Retrieval","created":"2022-10-21","cited_by_count":1}],"next_cursor":null}