{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"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":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2203.00859","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","created":"2022-03-02","cited_by_count":159},{"id":"1807.01653","title":"Latent Space Autoregression for Novelty Detection","created":"2018-07-04","cited_by_count":149},{"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":"1704.02447","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","created":"2017-04-08","cited_by_count":115},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111},{"id":"1805.04095","title":"Ordinal Depth Supervision for 3D Human Pose Estimation","created":"2018-05-10","cited_by_count":107},{"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":"1903.03295","title":"Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos","created":"2019-03-08","cited_by_count":104},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102},{"id":"1903.02330","title":"Self-Supervised Learning of 3D Human Pose using Multi-view Geometry","created":"2019-03-06","cited_by_count":98},{"id":"1912.11850","title":"Graph Embedded Pose Clustering for Anomaly Detection","created":"2019-12-26","cited_by_count":95},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"1704.04516","title":"Interpretable 3D Human Action Analysis with Temporal Convolutional Networks","created":"2017-04-14","cited_by_count":89},{"id":"2008.12328","title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","created":"2020-08-27","cited_by_count":86},{"id":"2107.13788","title":"Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows","created":"2021-07-29","cited_by_count":85},{"id":"2206.13028","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","created":"2022-06-27","cited_by_count":71},{"id":"2012.15175","title":"Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation","created":"2020-12-30","cited_by_count":69},{"id":"2306.05064","title":"K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization","created":"2023-06-08","cited_by_count":69},{"id":"2207.10172","title":"Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles","created":"2022-07-20","cited_by_count":62},{"id":"2211.10946","title":"Normalizing Flows for Human Pose Anomaly Detection","created":"2022-11-20","cited_by_count":60},{"id":"1908.04321","title":"Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection","created":"2019-08-12","cited_by_count":59},{"id":"2302.05087","title":"Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models","created":"2023-02-10","cited_by_count":59},{"id":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58},{"id":"1706.08276","title":"Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates","created":"2017-06-26","cited_by_count":54},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43},{"id":"2008.03791","title":"Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition","created":"2020-08-09","cited_by_count":36},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36},{"id":"2007.07227","title":"MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation","created":"2020-07-12","cited_by_count":35},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35},{"id":"1802.04920","title":"DVAE++: Discrete Variational Autoencoders with Overlapping Transformations","created":"2018-02-14","cited_by_count":32},{"id":"2112.04294","title":"A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos","created":"2021-12-08","cited_by_count":28},{"id":"1909.05704","title":"Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints","created":"2019-09-11","cited_by_count":25},{"id":"2012.13823","title":"Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition","created":"2020-12-26","cited_by_count":23},{"id":"2112.03649","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","created":"2021-12-07","cited_by_count":22},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22},{"id":"2211.00005","title":"Uncertainty-DTW for Time Series and Sequences","created":"2022-10-30","cited_by_count":21},{"id":"1805.07445","title":"DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors","created":"2018-05-18","cited_by_count":20},{"id":"2406.15395","title":"An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction","created":"2024-04-29","cited_by_count":19},{"id":"2004.11085","title":"SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition","created":"2020-04-23","cited_by_count":18},{"id":"2301.03561","title":"Ancilia: Scalable Intelligent Video Surveillance for the Artificial Intelligence of Things","created":"2023-01-09","cited_by_count":17},{"id":"1912.08435","title":"Self-Attention Network for Skeleton-based Human Action Recognition","created":"2019-12-18","cited_by_count":15},{"id":"2102.08997","title":"One-shot action recognition in challenging therapy scenarios","created":"2021-02-17","cited_by_count":15},{"id":"2303.05463","title":"Understanding the Challenges and Opportunities of Pose-based Anomaly Detection","created":"2023-03-09","cited_by_count":15},{"id":"1911.09217","title":"REVAMP$^2$T: Real-time Edge Video Analytics for Multi-camera Privacy-aware Pedestrian Tracking","created":"2019-11-20","cited_by_count":14},{"id":"2307.07286","title":"One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching","created":"2023-07-14","cited_by_count":12},{"id":"2209.10073","title":"Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition","created":"2022-09-21","cited_by_count":9},{"id":"2302.04310","title":"Understanding Policy and Technical Aspects of AI-Enabled Smart Video Surveillance to Address Public Safety","created":"2023-02-08","cited_by_count":9},{"id":"2111.06995","title":"A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition","created":"2021-11-13","cited_by_count":6}],"next_cursor":null}