{"list":"other","total":61,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"2310.06313","title":"Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models","created":"2023-10-10","cited_by_count":104},{"id":"2407.12705","title":"IMAGDressing-v1: Customizable Virtual Dressing","created":"2024-07-17","cited_by_count":100},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84},{"id":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80},{"id":"2008.01403","title":"Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization","created":"2020-08-04","cited_by_count":74},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65},{"id":"2412.12974","title":"Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance","created":"2024-12-17","cited_by_count":63},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62},{"id":"2407.01531","title":"Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning","created":"2024-07-01","cited_by_count":57},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57},{"id":"2407.02482","title":"Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models","created":"2024-07-02","cited_by_count":54},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53},{"id":"2411.09968","title":"Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs","created":"2024-11-15","cited_by_count":52},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"id":"2407.07614","title":"MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis","created":"2024-07-10","cited_by_count":44},{"id":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","cited_by_count":42},{"id":"2408.12928","title":"ParGo: Bridging Vision-Language with Partial and Global Views","created":"2024-08-23","cited_by_count":40},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37},{"id":"2111.10990","title":"Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification","created":"2021-11-22","cited_by_count":36},{"id":"2405.11613","title":"Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts","created":"2024-05-19","cited_by_count":36},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35},{"id":"2207.11934","title":"Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning","created":"2022-07-25","cited_by_count":33},{"id":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","cited_by_count":30},{"id":"2402.19014","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","created":"2024-02-29","cited_by_count":30},{"id":"2407.00737","title":"LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation","created":"2024-06-30","cited_by_count":30},{"id":"2308.10123","title":"3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation","created":"2023-08-19","cited_by_count":28},{"id":"2407.15130","title":"DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer","created":"2024-07-21","cited_by_count":27},{"id":"2301.01871","title":"Hypotheses Tree Building for One-Shot Temporal Sentence Localization","created":"2023-01-05","cited_by_count":25},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25},{"id":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","cited_by_count":18},{"id":"2305.14579","title":"Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning","created":"2023-05-23","cited_by_count":17},{"id":"2405.10530","title":"CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation","created":"2024-05-17","cited_by_count":17},{"id":"2207.13326","title":"Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing","created":"2022-07-27","cited_by_count":16},{"id":"2410.21352","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","created":"2024-10-28","cited_by_count":16},{"id":"2408.06158","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","created":"2024-08-12","cited_by_count":14},{"id":"2410.21170","title":"Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies","created":"2024-10-28","cited_by_count":14},{"id":"2012.05499","title":"Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation","created":"2020-12-10","cited_by_count":12},{"id":"2111.12994","title":"NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition","created":"2021-11-25","cited_by_count":12},{"id":"2407.03332","title":"DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learning","created":"2024-05-09","cited_by_count":10},{"id":"2408.12475","title":"Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition","created":"2024-08-22","cited_by_count":10},{"id":"2408.12469","title":"Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning","created":"2024-08-22","cited_by_count":8},{"id":"2412.20733","title":"Towards nation-wide analytical healthcare infrastructures: A privacy-preserving augmented knee rehabilitation case study","created":"2024-12-30","cited_by_count":8},{"id":"2207.04713","title":"GMN: Generative Multi-modal Network for Practical Document Information Extraction","created":"2022-07-11","cited_by_count":6},{"id":"2406.18591","title":"Composition Vision-Language Understanding via Segment and Depth Anything Model","created":"2024-06-07","cited_by_count":2}],"next_cursor":null}