{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137},{"id":"2009.03465","title":"LaSOT: A High-quality Large-scale Single Object Tracking Benchmark","created":"2020-09-08","cited_by_count":132},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131},{"id":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127},{"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},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126},{"id":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"2303.16580","title":"Generalized Relation Modeling for Transformer Tracking","created":"2023-03-29","cited_by_count":93},{"id":"2403.10574","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","created":"2024-03-15","cited_by_count":76},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75},{"id":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2303.12027","title":"Joint Visual Grounding and Tracking with Natural Language Specification","created":"2023-03-21","cited_by_count":59},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47},{"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},{"id":"2308.11322","title":"CiteTracker: Correlating Image and Text for Visual Tracking","created":"2023-08-22","cited_by_count":36},{"id":"1912.06316","title":"Grounding-Tracking-Integration","created":"2019-12-13","cited_by_count":32},{"id":"2203.15175","title":"Unified Transformer Tracker for Object Tracking","created":"2022-03-29","cited_by_count":31},{"id":"2401.11228","title":"Unifying Visual and Vision-Language Tracking via Contrastive Learning","created":"2024-01-20","cited_by_count":27},{"id":"1907.11751","title":"Real-time Visual Object Tracking with Natural Language Description","created":"2019-07-26","cited_by_count":26},{"id":"2403.03493","title":"VastTrack: Vast Category Visual Object Tracking","created":"2024-03-06","cited_by_count":26},{"id":"2503.23844","title":"FlexiMo: A Flexible Remote Sensing Foundation Model","created":"2025-03-31","cited_by_count":24},{"id":"2403.19975","title":"Context-Aware Integration of Language and Visual References for Natural Language Tracking","created":"2024-03-29","cited_by_count":22},{"id":"2405.19818","title":"WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark","created":"2024-05-30","cited_by_count":15},{"id":"2411.01756","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","created":"2024-11-04","cited_by_count":12},{"id":"2307.10046","title":"Divert More Attention to Vision-Language Object Tracking","created":"2023-07-19","cited_by_count":11},{"id":"2302.11867","title":"Transformers in Single Object Tracking: An Experimental Survey","created":"2023-02-23","cited_by_count":10},{"id":"2502.15199","title":"UrbanSAM: Learning Invariance-Inspired Adapters for Segment Anything Models in Urban Construction","created":"2025-02-21","cited_by_count":8}],"next_cursor":null}