{"total":112,"rows":[{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142,"area":null},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65,"area":null},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65,"area":null},{"id":"2201.10943","title":"Event-based Video Reconstruction via Potential-assisted Spiking Neural Network","created":"2022-01-25","cited_by_count":59,"area":null},{"id":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59,"area":null},{"id":"2211.11010","title":"Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric","created":"2022-11-20","cited_by_count":52,"area":null},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47,"area":null},{"id":"2305.15688","title":"Frame-Event Alignment and Fusion Network for High Frame Rate Tracking","created":"2023-05-25","cited_by_count":43,"area":null},{"id":"2308.04047","title":"SODFormer: Streaming Object Detection with Transformer Using Events and Frames","created":"2023-08-08","cited_by_count":39,"area":null},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30,"area":null},{"id":"2312.10692","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","created":"2023-12-17","cited_by_count":24,"area":null},{"id":"2304.14394","title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","created":"2023-04-27","cited_by_count":21,"area":null},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2308.04369","title":"SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition","created":"2023-08-08","cited_by_count":20,"area":null},{"id":"2312.08220","title":"EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset","created":"2023-12-13","cited_by_count":19,"area":null},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2401.02826","title":"CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras","created":"2024-01-05","cited_by_count":17,"area":null},{"id":"2407.05106","title":"DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition","created":"2024-07-06","cited_by_count":17,"area":null},{"id":"2311.00436","title":"Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion","created":"2023-11-01","cited_by_count":16,"area":null},{"id":"2506.05163","title":"FRED: The Florence RGB-Event Drone Dataset","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2507.05899","title":"What You Have is What You Track: Adaptive and Robust Multimodal Tracking","created":"2025-07-08","cited_by_count":15,"area":null},{"id":"2409.16099","title":"Neuromorphic Drone Detection: an Event-RGB Multimodal Approach","created":"2024-09-24","cited_by_count":14,"area":null},{"id":"2506.23575","title":"Event-based Tiny Object Detection: A Benchmark Dataset and Baseline","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2309.12842","title":"SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Events","created":"2023-09-22","cited_by_count":13,"area":null},{"id":"2503.08703","title":"SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks","created":"2025-03-09","cited_by_count":12,"area":null},{"id":"2203.14134","title":"RGBD Object Tracking: An In-depth Review","created":"2022-03-26","cited_by_count":11,"area":null},{"id":"2502.06583","title":"Adaptive Perception for Unified Visual Multi-modal Object Tracking","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2406.20024","title":"eMoE-Tracker: Environmental MoE-based Transformer for Robust Event-guided Object Tracking","created":"2024-06-28","cited_by_count":10,"area":null},{"id":"2505.19434","title":"CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2403.11875","title":"Towards Real-Time Fast Unmanned Aerial Vehicle Detection Using Dynamic Vision Sensors","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2405.05004","title":"TENet: Targetness Entanglement Incorporating with Multi-Scale Pooling and Mutually-Guided Fusion for RGB-E Object Tracking","created":"2024-05-08","cited_by_count":9,"area":null},{"id":"2405.17903","title":"Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2508.04564","title":"Drone Detection with Event Cameras","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2310.14194","title":"Distractor-aware Event-based Tracking","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2312.14446","title":"Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2403.05839","title":"Long-Term Visual Object Tracking with Event Cameras: An Associative Memory Augmented Tracker and A Benchmark Dataset","created":"2024-03-09","cited_by_count":8,"area":null},{"id":"2506.02448","title":"VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2403.11222","title":"SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2409.19342","title":"X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation","created":"2024-09-28","cited_by_count":7,"area":null},{"id":"2205.09676","title":"Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2308.11937","title":"Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2309.16987","title":"SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2407.21735","title":"EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching","created":"2024-07-31","cited_by_count":6,"area":null},{"id":"2409.11953","title":"Tracking Any Point with Frame-Event Fusion Network at High Frame Rate","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2505.20834","title":"Fully Spiking Neural Networks for Unified Frame-Event Object Tracking","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2303.14778","title":"RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning","created":"2023-03-26","cited_by_count":5,"area":null},{"id":"2312.11128","title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2312.16222","title":"Segment Any Events via Weighted Adaptation of Pivotal Tokens","created":"2023-12-24","cited_by_count":5,"area":null},{"id":"2409.03358","title":"MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice","created":"2024-09-05","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2306.05239","title":"Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2404.00548","title":"Modeling State Shifting via Local-Global Distillation for Event-Frame Gaze Tracking","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2503.06484","title":"Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithms","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2504.12576","title":"CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2406.18845","title":"Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2412.09105","title":"ResFlow: Fine-tuning Residual Optical Flow for Event-based High Temporal Resolution Motion Estimation","created":"2024-12-12","cited_by_count":3,"area":null},{"id":"2502.02334","title":"Event-aided Semantic Scene Completion","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2505.12903","title":"Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2601.23159","title":"Segment Any Events with Language","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2604.12502","title":"SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2409.17560","title":"Dynamic Subframe Splitting and Spatio-Temporal Motion Entangled Sparse Attention for RGB-E Tracking","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2505.12606","title":"Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2508.13000","title":"Omni Survey for Multimodality Analysis in Visual Object Tracking","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2508.18071","title":"EventTracer: Fast Path Tracing-based Event Stream Rendering","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2511.01427","title":"UniSOT: A Unified Framework for Multi-Modality Single Object Tracking","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2511.18344","title":"A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2511.21439","title":"EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.09016","title":"Learning to Remove Lens Flare in Event Camera","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2603.01412","title":"UETrack: A Unified and Efficient Framework for Single Object Tracking","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.03969","title":"Scaling Dense Event-Stream Pretraining from Visual Foundation Models","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2212.07754","title":"Event-based Visual Tracking in Dynamic Environments","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2310.06629","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2401.11123","title":"Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition","created":"2024-01-20","cited_by_count":1,"area":null},{"id":"2402.08936","title":"Predictive Temporal Attention on Event-based Video Stream for Energy-efficient Situation Awareness","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2502.18143","title":"LightFC-X: Lightweight Convolutional Tracker for RGB-X Tracking","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2502.18220","title":"UASTrack: A Unified Adaptive Selection Framework with Modality-Customization in Single Object Tracking","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.11218","title":"Towards General Multimodal Visual Tracking","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2504.05830","title":"Human Activity Recognition using RGB-Event based Sensors: A Multi-modal Heat Conduction Model and A Benchmark Dataset","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2505.19990","title":"Progressive Scaling Visual Object Tracking","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.23972","title":"Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2508.01592","title":"DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2508.02411","title":"HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2511.19475","title":"Tracking and Segmenting Anything in Any Modality","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2601.01022","title":"Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2603.14452","title":"Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2605.10496","title":"M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.31077","title":"AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2401.08068","title":"Representation Learning on Event Stream via an Elastic Net-incorporated Tensor Network","created":"2024-01-16","cited_by_count":0,"area":null},{"id":"2408.10488","title":"Event Stream-based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2409.12691","title":"A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2504.14423","title":"Adversarial Attack for RGB-Event based Visual Object Tracking","created":"2025-04-19","cited_by_count":0,"area":null},{"id":"2508.10655","title":"Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2508.17488","title":"Optimizing Multi-Modality Trackers via Significance-Regularized Tuning","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2512.22979","title":"PoseStreamer: A Multi-modal Framework for 3D Tracking of Unseen Moving Objects","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.06647","title":"eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2602.18258","title":"RoEL: Robust Event-based 3D Line Reconstruction","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.09287","title":"Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.21100","title":"Learning Progressive Adaptation for Multi-Modal Tracking","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.14526","title":"FreqTrack: Frequency Learning based Vision Transformer for RGB-Event Object Tracking","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.14094","title":"FEMOT: Multi-Object Tracking using Frame and Event Cameras","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":"100"}