{"total":112,"rows":[{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473,"area":null},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183,"area":"mllm"},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126,"area":null},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90,"area":null},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70,"area":"mllm"},{"id":"2409.10542","title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","created":"2024-09-01","cited_by_count":69,"area":"mllm"},{"id":"2203.15442","title":"Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding","created":"2022-03-29","cited_by_count":53,"area":"lr"},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2105.04281","title":"Visual Grounding with Transformers","created":"2021-05-10","cited_by_count":42,"area":null},{"id":"2209.13306","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","created":"2022-09-27","cited_by_count":42,"area":null},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2410.08145","title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs","created":"2024-10-10","cited_by_count":38,"area":"mllm"},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36,"area":null},{"id":"2103.12989","title":"Relation-aware Instance Refinement for Weakly Supervised Visual Grounding","created":"2021-03-24","cited_by_count":35,"area":null},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35,"area":null},{"id":"2103.07894","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","created":"2021-03-14","cited_by_count":33,"area":null},{"id":"2109.03413","title":"YouRefIt: Embodied Reference Understanding with Language and Gesture","created":"2021-09-08","cited_by_count":33,"area":null},{"id":"2401.00901","title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding","created":"2023-12-31","cited_by_count":32,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29,"area":null},{"id":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28,"area":null},{"id":"2410.08021","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2209.10304","title":"I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification","created":"2022-09-21","cited_by_count":27,"area":null},{"id":"2308.15512","title":"Shatter and Gather: Learning Referring Image Segmentation with Text Supervision","created":"2023-08-29","cited_by_count":25,"area":null},{"id":"2206.15462","title":"Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations","created":"2022-06-30","cited_by_count":24,"area":"mllm"},{"id":"2104.00492","title":"A Joint Network for Grasp Detection Conditioned on Natural Language Commands","created":"2021-04-01","cited_by_count":23,"area":null},{"id":"2207.08386","title":"Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding","created":"2022-07-18","cited_by_count":22,"area":null},{"id":"2311.05779","title":"Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter","created":"2023-11-09","cited_by_count":22,"area":null},{"id":"2106.04053","title":"Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding","created":"2021-06-08","cited_by_count":21,"area":null},{"id":"2204.03647","title":"Adapting CLIP For Phrase Localization Without Further Training","created":"2022-04-07","cited_by_count":21,"area":null},{"id":"2207.13450","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","created":"2022-07-27","cited_by_count":21,"area":null},{"id":"2103.05187","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","created":"2021-03-09","cited_by_count":20,"area":null},{"id":"2209.11972","title":"Ground then Navigate: Language-guided Navigation in Dynamic Scenes","created":"2022-09-24","cited_by_count":20,"area":null},{"id":"2203.08013","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2306.07515","title":"A Survey on Video Moment Localization","created":"2023-06-13","cited_by_count":18,"area":null},{"id":"2307.09267","title":"Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding","created":"2023-07-18","cited_by_count":18,"area":null},{"id":"2104.06008","title":"Disentangled Motif-aware Graph Learning for Phrase Grounding","created":"2021-04-13","cited_by_count":17,"area":null},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17,"area":null},{"id":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2207.01821","title":"Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2210.05668","title":"Understanding Embodied Reference with Touch-Line Transformer","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2211.14739","title":"MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14,"area":null},{"id":"2310.07056","title":"TextPSG: Panoptic Scene Graph Generation from Textual Descriptions","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2112.00475","title":"Weakly-Supervised Video Object Grounding via Causal Intervention","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2201.12596","title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning","created":"2022-01-29","cited_by_count":13,"area":"mllm"},{"id":"2103.03987","title":"Selective Replay Enhances Learning in Online Continual Analogical Reasoning","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2112.00967","title":"Relational Graph Learning for Grounded Video Description Generation","created":"2021-12-02","cited_by_count":12,"area":null},{"id":"2205.00949","title":"Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering","created":"2022-05-02","cited_by_count":12,"area":"lr"},{"id":"2502.20678","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2207.10400","title":"Correspondence Matters for Video Referring Expression Comprehension","created":"2022-07-21","cited_by_count":10,"area":null},{"id":"2501.17053","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","created":"2025-01-28","cited_by_count":10,"area":null},{"id":"2104.10412","title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","created":"2021-04-21","cited_by_count":9,"area":null},{"id":"2108.02562","title":"Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models","created":"2021-07-05","cited_by_count":8,"area":null},{"id":"2204.09957","title":"Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2311.06622","title":"TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System","created":"2023-11-11","cited_by_count":8,"area":"agents"},{"id":"2312.04539","title":"Auto-Vocabulary Semantic Segmentation","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2504.09623","title":"Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding","created":"2025-04-13","cited_by_count":8,"area":null},{"id":"2201.06686","title":"Unpaired Referring Expression Grounding via Bidirectional Cross-Modal Matching","created":"2022-01-18","cited_by_count":7,"area":null},{"id":"2402.09989","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","created":"2024-02-15","cited_by_count":7,"area":null},{"id":"2112.13031","title":"Grounding Linguistic Commands to Navigable Regions","created":"2021-12-24","cited_by_count":6,"area":null},{"id":"2210.13076","title":"Towards Unifying Reference Expression Generation and Comprehension","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2601.05244","title":"GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation","created":"2026-01-08","cited_by_count":6,"area":null},{"id":"2309.15523","title":"Improving Facade Parsing with Vision Transformers and Line Integration","created":"2023-09-27","cited_by_count":5,"area":null},{"id":"2104.10156","title":"Understanding Synonymous Referring Expressions via Contrastive Features","created":"2021-04-20","cited_by_count":4,"area":null},{"id":"2206.01627","title":"Pruning for Feature-Preserving Circuits in CNNs","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2210.02953","title":"Video Referring Expression Comprehension via Transformer with Content-aware Query","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2304.03669","title":"DATE: Domain Adaptive Product Seeker for E-commerce","created":"2023-04-07","cited_by_count":4,"area":null},{"id":"2310.16402","title":"Video Referring Expression Comprehension via Transformer with Content-conditioned Query","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2104.08614","title":"Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2206.06404","title":"Compositional Mixture Representations for Vision and Text","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2207.00744","title":"Gaussian Kernel-based Cross Modal Network for Spatio-Temporal Video Grounding","created":"2022-07-02","cited_by_count":3,"area":null},{"id":"2312.09625","title":"Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment","created":"2023-12-15","cited_by_count":3,"area":"mllm"},{"id":"2409.11919","title":"LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension","created":"2024-09-18","cited_by_count":3,"area":"mllm"},{"id":"2505.15123","title":"Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2507.16213","title":"Advancing Visual Large Language Model for Multi-granular Versatile Perception","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2510.14904","title":"CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2104.02605","title":"An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information","created":"2021-03-21","cited_by_count":2,"area":null},{"id":"2108.01056","title":"Distributed Attention for Grounded Image Captioning","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2201.02280","title":"Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping","created":"2022-01-07","cited_by_count":2,"area":null},{"id":"2201.09324","title":"Supervised Visual Attention for Simultaneous Multimodal Machine Translation","created":"2022-01-23","cited_by_count":2,"area":null},{"id":"2203.16682","title":"To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2205.12089","title":"Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2305.10913","title":"Weakly-Supervised Visual-Textual Grounding with Semantic Prior Refinement","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2406.16143","title":"Review of Zero-Shot and Few-Shot AI Algorithms in The Medical Domain","created":"2024-06-23","cited_by_count":2,"area":null},{"id":"2607.04605","title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval","created":"2026-07-06","cited_by_count":2,"area":"inference"},{"id":"2107.14593","title":"Neural Variational Learning for Grounded Language Acquisition","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2108.05308","title":"A Better Loss for Visual-Textual Grounding","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2210.00858","title":"Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach","created":"2022-10-03","cited_by_count":1,"area":"lr"},{"id":"2303.07545","title":"Implicit and Explicit Commonsense for Multi-sentence Video Captioning","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2303.16341","title":"Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2305.11497","title":"TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding","created":"2023-05-19","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}