{"total":57,"rows":[{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2209.01206","title":"Transformers in Remote Sensing: A Survey","created":"2022-09-02","cited_by_count":61,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2208.04309","title":"3D Vision with Transformers: A Survey","created":"2022-08-08","cited_by_count":21,"area":null},{"id":"2302.02316","title":"Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":17,"area":null},{"id":"2307.16897","title":"DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2402.08132","title":"On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era","created":"2024-02-12","cited_by_count":17,"area":null},{"id":"2308.04828","title":"Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning","created":"2023-08-09","cited_by_count":16,"area":null},{"id":"2308.09139","title":"The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation","created":"2023-08-17","cited_by_count":16,"area":null},{"id":"2306.17170","title":"An Overview on Generative AI at Scale with Edge-Cloud Computing","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2309.13851","title":"DISeR: Designing Imaging Systems with Reinforcement Learning","created":"2023-09-25","cited_by_count":6,"area":null},{"id":"2501.12681","title":"Can masking background and object reduce static bias for zero-shot action recognition?","created":"2025-01-22","cited_by_count":6,"area":null},{"id":"2211.04253","title":"Eat-Radar: Continuous Fine-Grained Intake Gesture Detection Using FMCW Radar and 3D Temporal Convolutional Network with Attention","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2310.16822","title":"Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2309.05943","title":"Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2403.19882","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2204.09166","title":"Performance Evaluation of Action Recognition Models on Low Quality Videos","created":"2022-04-19","cited_by_count":3,"area":null},{"id":"2210.04240","title":"Less is More: Facial Landmarks can Recognize a Spontaneous Smile","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2302.09585","title":"StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2404.18423","title":"OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2406.15034","title":"SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2409.06754","title":"Scaling Law Hypothesis for Multimodal Model","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2409.20083","title":"SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2508.01852","title":"Context Guided Transformer Entropy Modeling for Video Compression","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2604.10127","title":"VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2409.01216","title":"ESP-PCT: Enhanced VR Semantic Performance through Efficient Compression of Temporal and Spatial Redundancies in Point Cloud Transformers","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2410.00410","title":"Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2411.00630","title":"STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-based Video Models","created":"2024-11-01","cited_by_count":2,"area":null},{"id":"2212.05432","title":"Ego Vehicle Speed Estimation using 3D Convolution with Masked Attention","created":"2022-12-11","cited_by_count":1,"area":null},{"id":"2405.08344","title":"No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2407.03080","title":"Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2409.12924","title":"Wavelet GPT: Wavelet Inspired Large Language Models","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2502.15466","title":"Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2508.02978","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.16076","title":"Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2207.13306","title":"Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition","created":"2022-07-27","cited_by_count":0,"area":null},{"id":"2306.09331","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2307.13541","title":"Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2308.10533","title":"Joint learning of images and videos with a single Vision Transformer","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2311.10873","title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2409.01557","title":"TASL-Net: Tri-Attention Selective Learning Network for Intelligent Diagnosis of Bimodal Ultrasound Video","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2503.19002","title":"Quantum Complex-Valued Self-Attention Model","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2504.05783","title":"Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2508.02981","title":"MoExDA: Domain Adaptation for Edge-based Action Recognition","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2602.22923","title":"WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.00611","title":"Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2603.12887","title":"Forecasting Epileptic Seizures from Contactless Camera via Cross-Species Transfer Learning","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.26151","title":"Unsupervised Memory-Enhanced Video Transformers: Obstacle Detection for Autonomous Agricultural Rover","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.25452","title":"VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}