{"total":101,"rows":[{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86,"area":null},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69,"area":null},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"area":null},{"id":"2305.10724","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","created":"2023-05-18","cited_by_count":60,"area":null},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2408.04961","title":"In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation","created":"2024-08-09","cited_by_count":38,"area":null},{"id":"2405.03194","title":"CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario","created":"2024-05-06","cited_by_count":27,"area":null},{"id":"2407.14563","title":"Learning Visual Grounding from Generative Vision and Language Model","created":"2024-07-18","cited_by_count":27,"area":null},{"id":"2404.06362","title":"Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23,"area":null},{"id":"2406.10326","title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","created":"2024-06-14","cited_by_count":20,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2412.09283","title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption","created":"2024-12-12","cited_by_count":17,"area":null},{"id":"2310.05136","title":"InstructDET: Diversifying Referring Object Detection with Generalized Instructions","created":"2023-10-08","cited_by_count":16,"area":null},{"id":"2503.07485","title":"Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction","created":"2025-03-10","cited_by_count":16,"area":null},{"id":"2312.09738","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","created":"2023-12-15","cited_by_count":15,"area":null},{"id":"2408.02788","title":"GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2410.02244","title":"Visual Prompting in LLMs for Enhancing Emotion Recognition","created":"2024-10-03","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2502.20134","title":"Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2412.01539","title":"The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2505.24492","title":"Object Centric Concept Bottlenecks","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2507.02798","title":"No time to train! Training-Free Reference-Based Instance Segmentation","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9,"area":null},{"id":"2407.05578","title":"FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2504.17224","title":"Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2505.23769","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2512.17875","title":"Visually Prompted Benchmarks Are Surprisingly Fragile","created":"2025-12-19","cited_by_count":7,"area":null},{"id":"2403.06567","title":"Leveraging Foundation Models for Content-Based Image Retrieval in Radiology","created":"2024-03-11","cited_by_count":6,"area":null},{"id":"2406.03303","title":"Learning Visual Prompts for Guiding the Attention of Vision Transformers","created":"2024-06-05","cited_by_count":6,"area":null},{"id":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6,"area":null},{"id":"2410.19766","title":"Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition","created":"2024-10-13","cited_by_count":6,"area":null},{"id":"2412.11917","title":"Does VLM Classification Benefit from LLM Description Semantics?","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2601.02457","title":"PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding","created":"2026-01-05","cited_by_count":6,"area":null},{"id":"2504.00844","title":"PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2511.04601","title":"PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2310.06174","title":"Cost-Efficient Prompt Engineering for Unsupervised Entity Resolution","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2504.08806","title":"Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation","created":"2025-04-09","cited_by_count":4,"area":null},{"id":"2505.02867","title":"RESAnything: Attribute Prompting for Arbitrary Referring Segmentation","created":"2025-05-03","cited_by_count":4,"area":null},{"id":"2506.04650","title":"Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2509.04758","title":"Dynamic Group Detection using VLM-augmented Temporal Groupness Graph","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2310.13479","title":"Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2403.16539","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2407.12346","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2412.16897","title":"MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-Context","created":"2024-12-22","cited_by_count":3,"area":null},{"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":"2506.03799","title":"ConText: Driving In-context Learning for Text Removal and Segmentation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2508.10637","title":"Processing and acquisition traces in visual encoders: What does CLIP know about your camera?","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2603.23186","title":"ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2504.05305","title":"URECA: Unique Region Caption Anything","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2504.12542","title":"Post-Hurricane Debris Segmentation Using Fine-Tuned Foundational Vision Models","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2606.03951","title":"Demo2Tutorial: From Human Experience to Multimodal Software Tutorials","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2409.14095","title":"Foundation Models for Amodal Video Instance Segmentation in Automated Driving","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2501.17643","title":"Tonguescape: Exploring Language Models Understanding of Vowel Articulation","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2505.06280","title":"Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2506.10609","title":"MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2512.07245","title":"Zero-Shot Textual Explanations via Translating Decision-Critical Features","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2604.06748","title":"From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2606.03986","title":"NewtPhys: Do Foundation Models Understand Newtonian Physics?","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.19584","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.25537","title":"Visual prompt engineering for video models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2405.03852","title":"VSA4VQA: Scaling a Vector Symbolic Architecture to Visual Question Answering on Natural Images","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2412.06720","title":"VP-MEL: Visual Prompts Guided Multimodal Entity Linking","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2501.17171","title":"Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2504.01348","title":"Prompt-Guided Attention Head Selection for Focus-Oriented Image Retrieval","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2508.00589","title":"Context-based Motion Retrieval using Open Vocabulary Methods for Autonomous Driving","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.05411","title":"Personalizing Retrieval using Joint Embeddings or \"the Return of Fluffy\"","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2602.01527","title":"Toward a Machine Bertin: Why Visualization Needs Design Principles for Machine Cognition","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.25004","title":"Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.14069","title":"Towards Unconstrained Human-Object Interaction","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.21144","title":"Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.14705","title":"Towards Continuous Sign Language Conversation from Isolated Signs","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.16877","title":"Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.31597","title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.16124","title":"Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.16767","title":"Text-Vision Co-Instructed Image Editing","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.07264","title":"Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.08273","title":"Action- and Language-Conditioned Video Assessment for Embodied Control","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.08867","title":"Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.09053","title":"Diagnosing as Cardiologists Do: ECG Agents with Doctor-Grounded Priors for Clinical Reasoning Across Diseases and Populations","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.09147","title":"RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.15284","title":"VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.13254","title":"(How) Do MLLMs Report Bistable Images Like Humans?","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.31135","title":"Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":"100"}