{"total":48,"rows":[{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2207.07783","title":"Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection","created":"2022-07-15","cited_by_count":30,"area":null},{"id":"2206.03891","title":"PrivHAR: Recognizing Human Actions From Privacy-preserving Lens","created":"2022-06-08","cited_by_count":16,"area":null},{"id":"2410.21170","title":"Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2104.01198","title":"Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2210.13889","title":"Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2106.00050","title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","created":"2021-05-31","cited_by_count":9,"area":null},{"id":"2208.03934","title":"Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images","created":"2022-08-08","cited_by_count":8,"area":null},{"id":"2401.07942","title":"Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2206.15073","title":"COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings","created":"2022-06-30","cited_by_count":6,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2302.06848","title":"YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2404.14034","title":"PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2210.09441","title":"Real-Time Driver Monitoring Systems through Modality and View Analysis","created":"2022-10-17","cited_by_count":5,"area":null},{"id":"2212.14033","title":"How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection","created":"2022-12-28","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":"2201.10849","title":"Predicting Knee Osteoarthritis Progression from Structural MRI using Deep Learning","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2204.04674","title":"Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates","created":"2022-04-10","cited_by_count":4,"area":null},{"id":"2210.05952","title":"3D Brain and Heart Volume Generative Models: A Survey","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2208.12257","title":"Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2210.07983","title":"Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2401.03167","title":"PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations","created":"2024-01-06","cited_by_count":3,"area":null},{"id":"2504.06153","title":"A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning","created":"2025-04-08","cited_by_count":3,"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":"2210.11219","title":"YOWO-Plus: An Incremental Improvement","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2404.19668","title":"SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2509.07525","title":"EHWGesture -- A dataset for multimodal understanding of clinical gestures","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2602.19994","title":"RADE-Net: Robust Attention Network for Radar-Only Object Detection in Adverse Weather","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2109.02137","title":"Efficient Action Recognition Using Confidence Distillation","created":"2021-09-05","cited_by_count":1,"area":null},{"id":"2210.05104","title":"3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2308.04643","title":"Long-Distance Gesture Recognition using Dynamic Neural Networks","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2409.05260","title":"Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space","created":"2024-09-09","cited_by_count":1,"area":null},{"id":"2501.14495","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2512.15707","title":"GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2103.08457","title":"RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2104.10492","title":"Skimming and Scanning for Untrimmed Video Action Recognition","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2108.13153","title":"LIGAR: Lightweight General-purpose Action Recognition","created":"2021-08-30","cited_by_count":0,"area":null},{"id":"2208.06966","title":"STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval","created":"2022-08-15","cited_by_count":0,"area":null},{"id":"2305.07812","title":"Lightweight Delivery Detection on Doorbell Cameras","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2306.13474","title":"Efficient Online Processing with Deep Neural Networks","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2306.15619","title":"DCID: Deep Canonical Information Decomposition","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2405.01337","title":"Multi-view Action Recognition via Directed Gromov-Wasserstein Discrepancy","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2407.12805","title":"Dark Transformer: A Video Transformer for Action Recognition in the Dark","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2407.14464","title":"AttentNet: Fully Convolutional 3D Attention for Lung Nodule Detection","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2408.02623","title":"YOWOv3: An Efficient and Generalized Framework for Human Action Detection and Recognition","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2503.07419","title":"Analysis of 3D Urticaceae Pollen Classification Using Deep Learning Models","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2602.21613","title":"Virtual Biopsy for Intracranial Tumors Diagnosis on MRI","created":"2026-02-25","cited_by_count":0,"area":null}],"next_cursor":null}