{"list":"other","total":79,"rows":[{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93},{"id":"1903.00839","title":"Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing","created":"2019-03-03","cited_by_count":88},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81},{"id":"1908.07129","title":"Zero-Shot Grounding of Objects from Natural Language Queries","created":"2019-08-20","cited_by_count":79},{"id":"2311.18231","title":"TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model","created":"2023-11-30","cited_by_count":76},{"id":"1612.09542","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","created":"2016-12-30","cited_by_count":74},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74},{"id":"1901.00850","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","created":"2019-01-03","cited_by_count":73},{"id":"2401.02361","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","created":"2024-01-04","cited_by_count":65},{"id":"1912.10664","title":"Scale Match for Tiny Person Detection","created":"2019-12-23","cited_by_count":61},{"id":"2309.07439","title":"DePT: Decoupled Prompt Tuning","created":"2023-09-14","cited_by_count":58},{"id":"1711.06370","title":"Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries","created":"2017-11-17","cited_by_count":56},{"id":"1701.03439","title":"Comprehension-guided referring expressions","created":"2017-01-12","cited_by_count":52},{"id":"2210.02390","title":"Bayesian Prompt Learning for Image-Language Model Generalization","created":"2022-10-05","cited_by_count":51},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36},{"id":"2309.03406","title":"Distribution-Aware Prompt Tuning for Vision-Language Models","created":"2023-09-06","cited_by_count":35},{"id":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31},{"id":"2211.15516","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","created":"2022-11-28","cited_by_count":24},{"id":"2308.12035","title":"RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D","created":"2023-08-23","cited_by_count":21},{"id":"2305.00603","title":"Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation","created":"2023-04-30","cited_by_count":18},{"id":"2307.11558","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","created":"2023-07-21","cited_by_count":17},{"id":"2406.06820","title":"Adapters Strike Back","created":"2024-06-10","cited_by_count":16},{"id":"2103.12346","title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","created":"2021-03-23","cited_by_count":11}],"next_cursor":null}