{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"1612.02295","title":"Large-Margin Softmax Loss for Convolutional Neural Networks","created":"2016-12-07","cited_by_count":296},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"1803.05598","title":"Large Margin Deep Networks for Classification","created":"2018-03-15","cited_by_count":112},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106},{"id":"1703.08274","title":"View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data","created":"2017-03-24","cited_by_count":105},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"1804.07453","title":"View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition","created":"2018-04-20","cited_by_count":84},{"id":"2007.14690","title":"Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition","created":"2020-07-29","cited_by_count":82},{"id":"2012.06399","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","created":"2020-12-11","cited_by_count":77},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77},{"id":"1703.05908","title":"Learning Robust Visual-Semantic Embeddings","created":"2017-03-17","cited_by_count":56},{"id":"2210.04388","title":"Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization","created":"2022-10-10","cited_by_count":50},{"id":"1907.13025","title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","created":"2019-07-30","cited_by_count":43},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43},{"id":"2103.13582","title":"Learning Dynamic Alignment via Meta-filter for Few-shot Learning","created":"2021-03-25","cited_by_count":41},{"id":"2009.00210","title":"Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition","created":"2020-09-01","cited_by_count":37},{"id":"2207.10856","title":"Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation","created":"2022-07-22","cited_by_count":33},{"id":"1511.04458","title":"Transductive Zero-Shot Action Recognition by Word-Vector Embedding","created":"2015-11-13","cited_by_count":31},{"id":"2112.04178","title":"Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition","created":"2021-12-08","cited_by_count":29},{"id":"2101.11530","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","created":"2021-01-27","cited_by_count":24},{"id":"2308.03950","title":"Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization","created":"2023-08-07","cited_by_count":24},{"id":"1911.11344","title":"Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space","created":"2019-11-26","cited_by_count":19},{"id":"2307.07286","title":"One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching","created":"2023-07-14","cited_by_count":12}],"next_cursor":null}