{"total":180,"rows":[{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350,"area":null},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281,"area":null},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220,"area":null},{"id":"2104.10475","title":"Camouflaged Object Segmentation with Distraction Mining","created":"2021-04-21","cited_by_count":151,"area":null},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131,"area":null},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129,"area":null},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126,"area":null},{"id":"2203.05328","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","created":"2022-03-10","cited_by_count":119,"area":null},{"id":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117,"area":null},{"id":"2104.00324","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","created":"2021-04-01","cited_by_count":91,"area":null},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82,"area":null},{"id":"2308.05140","title":"Robust Object Modeling for Visual Tracking","created":"2023-08-09","cited_by_count":80,"area":null},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75,"area":null},{"id":"2108.00202","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","created":"2021-07-31","cited_by_count":72,"area":null},{"id":"2203.01885","title":"TCTrack: Temporal Contexts for Aerial Tracking","created":"2022-03-03","cited_by_count":69,"area":null},{"id":"2108.04728","title":"Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds","created":"2021-08-10","cited_by_count":66,"area":null},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62,"area":null},{"id":"2303.12027","title":"Joint Visual Grounding and Tracking with Natural Language Specification","created":"2023-03-21","cited_by_count":59,"area":null},{"id":"2203.06883","title":"Accelerating DETR Convergence via Semantic-Aligned Matching","created":"2022-03-14","cited_by_count":58,"area":null},{"id":"2203.10541","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","created":"2022-03-20","cited_by_count":56,"area":null},{"id":"2203.01730","title":"Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds","created":"2022-03-03","cited_by_count":55,"area":null},{"id":"2111.04426","title":"3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds","created":"2021-11-08","cited_by_count":54,"area":null},{"id":"2112.02838","title":"Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook","created":"2021-12-06","cited_by_count":46,"area":null},{"id":"2108.05630","title":"3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud","created":"2021-08-12","cited_by_count":45,"area":null},{"id":"2207.11995","title":"3D Siamese Transformer Network for Single Object Tracking on Point Clouds","created":"2022-07-25","cited_by_count":44,"area":null},{"id":"2106.08816","title":"SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking","created":"2021-06-16","cited_by_count":38,"area":null},{"id":"2112.07957","title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","created":"2021-12-15","cited_by_count":38,"area":null},{"id":"2203.11191","title":"Robust Visual Tracking by Segmentation","created":"2022-03-21","cited_by_count":38,"area":null},{"id":"2308.11894","title":"Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack","created":"2023-08-23","cited_by_count":37,"area":null},{"id":"2308.11322","title":"CiteTracker: Correlating Image and Text for Visual Tracking","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2101.08466","title":"Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking","created":"2021-01-21","cited_by_count":31,"area":null},{"id":"2203.15175","title":"Unified Transformer Tracker for Object Tracking","created":"2022-03-29","cited_by_count":31,"area":null},{"id":"2309.03979","title":"Separable Self and Mixed Attention Transformers for Efficient Object Tracking","created":"2023-09-07","cited_by_count":31,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2108.03637","title":"Saliency-Associated Object Tracking","created":"2021-08-08","cited_by_count":30,"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":"2101.08446","title":"All-Day Object Tracking for Unmanned Aerial Vehicle","created":"2021-01-21","cited_by_count":28,"area":null},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26,"area":null},{"id":"2308.10330","title":"Towards Real-World Visual Tracking with Temporal Contexts","created":"2023-08-20","cited_by_count":26,"area":null},{"id":"2403.03493","title":"VastTrack: Vast Category Visual Object Tracking","created":"2024-03-06","cited_by_count":26,"area":null},{"id":"2201.02526","title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","created":"2022-01-07","cited_by_count":25,"area":null},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2503.06625","title":"Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking","created":"2025-03-09","cited_by_count":23,"area":null},{"id":"2108.12711","title":"Learning to Track Objects from Unlabeled Videos","created":"2021-08-28","cited_by_count":21,"area":null},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21,"area":null},{"id":"2303.04378","title":"SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking","created":"2023-03-08","cited_by_count":20,"area":null},{"id":"2111.12960","title":"Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark","created":"2021-11-25","cited_by_count":18,"area":null},{"id":"2202.13073","title":"Global Instance Tracking: Locating Target More Like Humans","created":"2022-02-26","cited_by_count":18,"area":null},{"id":"2103.16086","title":"Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking","created":"2021-03-30","cited_by_count":17,"area":null},{"id":"2204.01475","title":"Unsupervised Learning of Accurate Siamese Tracking","created":"2022-04-04","cited_by_count":16,"area":null},{"id":"2302.07344","title":"Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2309.10491","title":"DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs","created":"2023-09-19","cited_by_count":16,"area":null},{"id":"2104.00829","title":"Learning to Filter: Siamese Relation Network for Robust Tracking","created":"2021-04-02","cited_by_count":15,"area":null},{"id":"2110.08822","title":"Siamese Transformer Pyramid Networks for Real-Time UAV Tracking","created":"2021-10-17","cited_by_count":15,"area":null},{"id":"2105.03817","title":"TrTr: Visual Tracking with Transformer","created":"2021-05-09","cited_by_count":14,"area":null},{"id":"2107.12085","title":"Learning to Adversarially Blur Visual Object Tracking","created":"2021-07-26","cited_by_count":14,"area":null},{"id":"2109.09883","title":"On the Importance of Distractors for Few-Shot Classification","created":"2021-09-20","cited_by_count":14,"area":null},{"id":"2302.03679","title":"How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2303.12535","title":"An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13,"area":null},{"id":"2207.02088","title":"SiamMask: A Framework for Fast Online Object Tracking and Segmentation","created":"2022-07-05","cited_by_count":13,"area":null},{"id":"2208.05810","title":"Towards Sequence-Level Training for Visual Tracking","created":"2022-08-11","cited_by_count":13,"area":null},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12,"area":null},{"id":"2203.05928","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2103.07302","title":"Siamese Infrared and Visible Light Fusion Network for RGB-T Tracking","created":"2021-03-12","cited_by_count":11,"area":null},{"id":"2104.12041","title":"Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy","created":"2021-04-25","cited_by_count":11,"area":null},{"id":"2203.14134","title":"RGBD Object Tracking: An In-depth Review","created":"2022-03-26","cited_by_count":11,"area":null},{"id":"2205.04281","title":"Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis","created":"2022-05-09","cited_by_count":11,"area":null},{"id":"2207.08044","title":"DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking","created":"2022-07-17","cited_by_count":11,"area":null},{"id":"2307.14630","title":"360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking","created":"2023-07-27","cited_by_count":11,"area":null},{"id":"2503.12888","title":"UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Network","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2106.10900","title":"Self-Supervised Tracking via Target-Aware Data Synthesis","created":"2021-06-21","cited_by_count":10,"area":null},{"id":"2204.07414","title":"SOTVerse: A User-defined Task Space of Single Object Tracking","created":"2022-04-15","cited_by_count":10,"area":null},{"id":"2205.11761","title":"Ranking-Based Siamese Visual Tracking","created":"2022-05-24","cited_by_count":10,"area":null},{"id":"2302.11867","title":"Transformers in Single Object Tracking: An Experimental Survey","created":"2023-02-23","cited_by_count":10,"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":"2105.11237","title":"SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking","created":"2021-05-24","cited_by_count":9,"area":null},{"id":"2409.16652","title":"Progressive Representation Learning for Real-Time UAV Tracking","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2409.18901","title":"Improving Visual Object Tracking through Visual Prompting","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2203.16092","title":"Global Tracking via Ensemble of Local Trackers","created":"2022-03-30","cited_by_count":8,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","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":"2312.16250","title":"A Comprehensive Study of Object Tracking in Low-Light Environments","created":"2023-12-25","cited_by_count":8,"area":null},{"id":"2404.13953","title":"360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos","created":"2024-04-22","cited_by_count":8,"area":null},{"id":"2104.00403","title":"Target Transformed Regression for Accurate Tracking","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2104.14805","title":"Few-Shot Video Object Detection","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2106.04840","title":"Tracking by Joint Local and Global Search: A Target-aware Attention based Approach","created":"2021-06-09","cited_by_count":7,"area":null},{"id":"2111.04264","title":"Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2204.14093","title":"Learning Localization-aware Target Confidence for Siamese Visual Tracking","created":"2022-04-29","cited_by_count":7,"area":null},{"id":"2207.14172","title":"Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2301.01482","title":"Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles","created":"2023-01-04","cited_by_count":7,"area":null},{"id":"2104.07303","title":"SiamCorners: Siamese Corner Networks for Visual Tracking","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2108.04521","title":"Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking","created":"2021-08-10","cited_by_count":6,"area":null},{"id":"2110.01812","title":"UHP-SOT: An Unsupervised High-Performance Single Object Tracker","created":"2021-10-05","cited_by_count":6,"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":"2208.00662","title":"Local Perception-Aware Transformer for Aerial Tracking","created":"2022-08-01","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":"2406.05810","title":"ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving","created":"2024-06-09","cited_by_count":6,"area":null}],"next_cursor":"100"}