{"total":109,"rows":[{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263,"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":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"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":"2108.00202","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","created":"2021-07-31","cited_by_count":72,"area":null},{"id":"2301.13018","title":"DELTA: degradation-free fully test-time adaptation","created":"2023-01-30","cited_by_count":72,"area":null},{"id":"2108.00803","title":"Learn to Match: Automatic Matching Network Design for Visual Tracking","created":"2021-08-02","cited_by_count":67,"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":"2203.10541","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","created":"2022-03-20","cited_by_count":56,"area":null},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"area":null},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47,"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":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41,"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":"2104.03507","title":"Progressive Temporal Feature Alignment Network for Video Inpainting","created":"2021-04-08","cited_by_count":35,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"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":"2309.03979","title":"Separable Self and Mixed Attention Transformers for Efficient Object Tracking","created":"2023-09-07","cited_by_count":31,"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":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25,"area":null},{"id":"2305.13495","title":"Type-to-Track: Retrieve Any Object via Prompt-based Tracking","created":"2023-05-22","cited_by_count":24,"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":"2101.08040","title":"1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking","created":"2021-01-20","cited_by_count":17,"area":null},{"id":"2307.01024","title":"SAM-DA: UAV Tracks Anything at Night with SAM-Powered Domain Adaptation","created":"2023-07-03","cited_by_count":17,"area":null},{"id":"2205.08987","title":"Trading Positional Complexity vs. Deepness in Coordinate Networks","created":"2022-05-18","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","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":"2105.03817","title":"TrTr: Visual Tracking with Transformer","created":"2021-05-09","cited_by_count":14,"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":"2203.14463","title":"Large-scale Bilingual Language-Image Contrastive Learning","created":"2022-03-28","cited_by_count":12,"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":"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":"2307.10046","title":"Divert More Attention to Vision-Language Object Tracking","created":"2023-07-19","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":"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":"2302.11867","title":"Transformers in Single Object Tracking: An Experimental Survey","created":"2023-02-23","cited_by_count":10,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","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":"2507.23473","title":"CST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2104.14805","title":"Few-Shot Video Object Detection","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2106.06736","title":"Multi-level Attention Fusion Network for Audio-visual Event Recognition","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2109.01800","title":"A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion","created":"2021-09-04","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":"2301.10057","title":"Planar Object Tracking via Weighted Optical Flow","created":"2023-01-24","cited_by_count":7,"area":null},{"id":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2404.08778","title":"Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset","created":"2024-04-12","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":"2208.00662","title":"Local Perception-Aware Transformer for Aerial Tracking","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2108.03821","title":"Video Annotation for Visual Tracking via Selection and Refinement","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2201.13066","title":"Single Object Tracking: A Survey of Methods, Datasets, and Evaluation Metrics","created":"2022-01-31","cited_by_count":5,"area":null},{"id":"2302.00930","title":"Adaptive Siamese Tracking with a Compact Latent Network","created":"2023-02-02","cited_by_count":5,"area":null},{"id":"2403.10499","title":"Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2107.02393","title":"MSE Loss with Outlying Label for Imbalanced Classification","created":"2021-07-06","cited_by_count":3,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2111.10737","title":"3D Visual Tracking Framework with Deep Learning for Asteroid Exploration","created":"2021-11-21","cited_by_count":3,"area":null},{"id":"2403.05852","title":"SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Tracking","created":"2024-03-09","cited_by_count":3,"area":null},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2606.04665","title":"Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2103.12924","title":"Benchmarking Deep Trackers on Aerial Videos","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2104.15049","title":"Updatable Siamese Tracker with Two-stage One-shot Learning","created":"2021-04-30","cited_by_count":2,"area":null},{"id":"2106.07862","title":"Domain Adaptive SiamRPN++ for Object Tracking in the Wild","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2211.08249","title":"Explaining Cross-Domain Recognition with Interpretable Deep Classifier","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2507.22361","title":"Object Recognition Datasets and Challenges: A Review","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2510.14666","title":"Geometric Moment Alignment for Domain Adaptation via Siegel Embeddings","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2103.10130","title":"Real-Time Visual Object Tracking via Few-Shot Learning","created":"2021-03-18","cited_by_count":1,"area":null},{"id":"2107.05005","title":"Towards Accurate Localization by Instance Search","created":"2021-07-11","cited_by_count":1,"area":null},{"id":"2211.08894","title":"AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation","created":"2022-11-16","cited_by_count":1,"area":null},{"id":"2211.14564","title":"Siamese Object Tracking for Vision-Based UAM Approaching with Pairwise Scale-Channel Attention","created":"2022-11-26","cited_by_count":1,"area":null},{"id":"2310.02201","title":"Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2404.06247","title":"LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks","created":"2024-04-09","cited_by_count":1,"area":null},{"id":"2406.07693","title":"A Labelled Dataset for Sentiment Analysis of Videos on YouTube, TikTok, and Other Sources about the 2024 Outbreak of Measles","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2406.09564","title":"Towards Domain Adaptive Neural Contextual Bandits","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2509.02182","title":"ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2604.10527","title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2608.30762","title":"ChessQueries: Toward Better Chess Board Recognition","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2103.10089","title":"Higher Performance Visual Tracking with Dual-Modal Localization","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2105.02408","title":"Spatio-Temporal Matching for Siamese Visual Tracking","created":"2021-05-06","cited_by_count":0,"area":null},{"id":"2110.11739","title":"UBR$^2$S: Uncertainty-Based Resampling and Reweighting Strategy for Unsupervised Domain Adaptation","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2110.12194","title":"RPT++: Customized Feature Representation for Siamese Visual Tracking","created":"2021-10-23","cited_by_count":0,"area":null},{"id":"2111.02901","title":"Certainty Volume Prediction for Unsupervised Domain Adaptation","created":"2021-11-03","cited_by_count":0,"area":null},{"id":"2202.03206","title":"Recent Trends in 2D Object Detection and Applications in Video Event Recognition","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2202.04966","title":"Real-Time Siamese Multiple Object Tracker with Enhanced Proposals","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2203.01531","title":"CAFE: Learning to Condense Dataset by Aligning Features","created":"2022-03-03","cited_by_count":0,"area":null},{"id":"2206.07998","title":"Differentially Private Multi-Party Data Release for Linear Regression","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2309.09078","title":"Unsupervised Green Object Tracker (GOT) without Offline Pre-training","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2310.04757","title":"CAD Models to Real-World Images: A Practical Approach to Unsupervised Domain Adaptation in Industrial Object Classification","created":"2023-10-07","cited_by_count":0,"area":null},{"id":"2404.09504","title":"Learning Tracking Representations from Single Point Annotations","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2405.10439","title":"Beyond Traditional Single Object Tracking: A Survey","created":"2024-05-16","cited_by_count":0,"area":null},{"id":"2406.05131","title":"A Semi-Self-Supervised Approach for Dense-Pattern Video Object Segmentation","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2406.17183","title":"POPCat: Propagation of particles for complex annotation tasks","created":"2024-06-24","cited_by_count":0,"area":null}],"next_cursor":"100"}