{"list":"other","total":85,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"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":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"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":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"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":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"1505.00256","title":"DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving","created":"2015-05-01","cited_by_count":231},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217},{"id":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"id":"1510.07945","title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking","created":"2015-10-27","cited_by_count":209},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"2406.19435","title":"A Sanity Check for AI-generated Image Detection","created":"2024-06-27","cited_by_count":189},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"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":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"id":"2303.16580","title":"Generalized Relation Modeling for Transformer Tracking","created":"2023-03-29","cited_by_count":93},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89},{"id":"2004.00305","title":"High-Performance Long-Term Tracking with Meta-Updater","created":"2020-04-01","cited_by_count":80},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65},{"id":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59},{"id":"2312.17133","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","created":"2023-12-28","cited_by_count":59},{"id":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","cited_by_count":54},{"id":"2308.06904","title":"Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking","created":"2023-08-14","cited_by_count":53},{"id":"2408.10700","title":"AnyGraph: Graph Foundation Model in the Wild","created":"2024-08-20","cited_by_count":53},{"id":"2206.04664","title":"On Data Scaling in Masked Image Modeling","created":"2022-06-09","cited_by_count":46},{"id":"2208.09787","title":"RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking","created":"2022-08-21","cited_by_count":42},{"id":"1512.06735","title":"Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs","created":"2015-12-21","cited_by_count":32},{"id":"2309.03979","title":"Separable Self and Mixed Attention Transformers for Efficient Object Tracking","created":"2023-09-07","cited_by_count":31},{"id":"2501.16404","title":"DynaPrompt: Dynamic Test-Time Prompt Tuning","created":"2025-01-27","cited_by_count":31},{"id":"2208.06888","title":"AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility","created":"2022-08-14","cited_by_count":22},{"id":"2202.13073","title":"Global Instance Tracking: Locating Target More Like Humans","created":"2022-02-26","cited_by_count":18},{"id":"2309.12303","title":"PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation","created":"2023-09-21","cited_by_count":18},{"id":"2311.18835","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","created":"2023-11-30","cited_by_count":14},{"id":"2402.14392","title":"Reading Relevant Feature from Global Representation Memory for Visual Object Tracking","created":"2024-02-22","cited_by_count":12},{"id":"2202.05659","title":"Tiny Object Tracking: A Large-scale Dataset and A Baseline","created":"2022-02-11","cited_by_count":11},{"id":"2212.11920","title":"Beyond SOT: Tracking Multiple Generic Objects at Once","created":"2022-12-22","cited_by_count":11},{"id":"2505.17020","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","created":"2025-05-22","cited_by_count":11},{"id":"2408.11795","title":"EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model","created":"2024-08-21","cited_by_count":10},{"id":"2409.17564","title":"General Compression Framework for Efficient Transformer Object Tracking","created":"2024-09-26","cited_by_count":10},{"id":"2501.02467","title":"DeTrack: In-model Latent Denoising Learning for Visual Object Tracking","created":"2025-01-05","cited_by_count":5}],"next_cursor":null}