{"total":24,"rows":[{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2111.13241","title":"Learning from Temporal Gradient for Semi-supervised Action Recognition","created":"2021-11-25","cited_by_count":26,"area":null},{"id":"2406.11836","title":"RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2208.09424","title":"Hierarchical Compositional Representations for Few-shot Action Recognition","created":"2022-08-19","cited_by_count":10,"area":null},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2106.14403","title":"A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images","created":"2021-06-28","cited_by_count":6,"area":null},{"id":"2102.00565","title":"CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning","created":"2021-01-31","cited_by_count":5,"area":null},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2108.12957","title":"Searching for Two-Stream Models in Multivariate Space for Video Recognition","created":"2021-08-30","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2105.09909","title":"PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection","created":"2021-05-06","cited_by_count":2,"area":null},{"id":"2207.05331","title":"Robotic Detection of a Human-Comprehensible Gestural Language for Underwater Multi-Human-Robot Collaboration","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2107.12618","title":"Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021","created":"2021-07-27","cited_by_count":1,"area":null},{"id":"2108.03375","title":"Temporal Action Localization Using Gated Recurrent Units","created":"2021-08-07","cited_by_count":1,"area":null},{"id":"2208.05034","title":"Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2212.03384","title":"DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2212.11030","title":"Deep set conditioned latent representations for action recognition","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2211.05531","title":"SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2301.06082","title":"A Survey on Human Action Recognition","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2606.12374","title":"Semantically-Aware Diver Activity Recognition Framework for Effective Underwater Multi-Human-Robot Collaboration","created":"2026-06-10","cited_by_count":0,"area":null}],"next_cursor":null}