{"list":"other","total":62,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"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":"1412.6622","title":"Deep metric learning using Triplet network","created":"2014-12-20","cited_by_count":422},{"id":"1804.02815","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","created":"2018-04-09","cited_by_count":371},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"2303.15233","title":"Text-to-Image Diffusion Models are Zero-Shot Classifiers","created":"2023-03-27","cited_by_count":143},{"id":"2308.12469","title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","created":"2023-08-23","cited_by_count":131},{"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":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85},{"id":"2211.16487","title":"DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models","created":"2022-11-29","cited_by_count":65},{"id":"1603.07772","title":"Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks","created":"2016-03-24","cited_by_count":63},{"id":"2303.03729","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","created":"2023-03-07","cited_by_count":62},{"id":"1703.05908","title":"Learning Robust Visual-Semantic Embeddings","created":"2017-03-17","cited_by_count":56},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43},{"id":"2303.14474","title":"3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition","created":"2023-03-25","cited_by_count":40},{"id":"2211.13224","title":"Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors","created":"2022-11-23","cited_by_count":34},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31},{"id":"1906.09955","title":"A Comparative Review of Recent Kinect-based Action Recognition Algorithms","created":"2019-06-24","cited_by_count":29},{"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":"2406.13327","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","created":"2024-06-19","cited_by_count":23},{"id":"1909.06423","title":"Zero-Shot Action Recognition in Videos: A Survey","created":"2019-09-13","cited_by_count":19},{"id":"2404.07487","title":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","created":"2024-04-11","cited_by_count":19},{"id":"2407.13460","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","created":"2024-07-18","cited_by_count":19},{"id":"2212.04761","title":"Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition","created":"2022-12-09","cited_by_count":13},{"id":"2404.01051","title":"Action Detection via an Image Diffusion Process","created":"2024-04-01","cited_by_count":11},{"id":"2309.09592","title":"Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition","created":"2023-09-18","cited_by_count":9},{"id":"2409.14336","title":"Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment","created":"2024-09-22","cited_by_count":9},{"id":"2308.07571","title":"Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition","created":"2023-08-15","cited_by_count":7},{"id":"2406.00639","title":"An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition","created":"2024-06-02","cited_by_count":7},{"id":"2311.17072","title":"IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers","created":"2023-11-27","cited_by_count":2}],"next_cursor":null}