{"total":76,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75,"area":null},{"id":"2402.18206","title":"Balancing Act: Distribution-Guided Debiasing in Diffusion Models","created":"2024-02-28","cited_by_count":52,"area":"diffusion"},{"id":"2103.15545","title":"Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models","created":"2021-03-29","cited_by_count":51,"area":null},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48,"area":null},{"id":"2310.06823","title":"NECO: NEural Collapse Based Out-of-distribution detection","created":"2023-10-10","cited_by_count":42,"area":null},{"id":"2310.13923","title":"Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation","created":"2023-10-21","cited_by_count":38,"area":null},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"area":null},{"id":"2210.11464","title":"Self-Supervised Learning via Maximum Entropy Coding","created":"2022-10-20","cited_by_count":33,"area":null},{"id":"2305.18262","title":"Beyond Confidence: Reliable Models Should Also Consider Atypicality","created":"2023-05-29","cited_by_count":25,"area":null},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2503.12652","title":"UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing","created":"2025-03-16","cited_by_count":19,"area":"diffusion"},{"id":"2209.05980","title":"Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation","created":"2022-09-13","cited_by_count":16,"area":null},{"id":"2306.03715","title":"Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability","created":"2023-06-06","cited_by_count":16,"area":null},{"id":"2411.03359","title":"Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection","created":"2024-11-05","cited_by_count":15,"area":"mllm"},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2105.07484","title":"Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild","created":"2021-05-16","cited_by_count":12,"area":null},{"id":"2312.04837","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","created":"2023-12-08","cited_by_count":12,"area":"distill"},{"id":"2406.06133","title":"ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models","created":"2024-06-10","cited_by_count":12,"area":"diffusion"},{"id":"2505.18699","title":"Affective Image Editing: Shaping Emotional Factors via Text Descriptions","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2202.07861","title":"Practical Network Acceleration with Tiny Sets","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2209.03268","title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing","created":"2022-09-07","cited_by_count":8,"area":null},{"id":"2403.13870","title":"ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations","created":"2024-03-20","cited_by_count":8,"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":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2411.14049","title":"Out-Of-Distribution Detection with Diversification (Provably)","created":"2024-11-21","cited_by_count":6,"area":null},{"id":"2107.07148","title":"What Image Features Boost Housing Market Predictions?","created":"2021-07-15","cited_by_count":5,"area":null},{"id":"2203.04446","title":"Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition","created":"2022-03-08","cited_by_count":5,"area":null},{"id":"2501.11485","title":"SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models","created":"2025-01-20","cited_by_count":5,"area":"mllm"},{"id":"2103.09435","title":"Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks","created":"2021-03-17","cited_by_count":4,"area":null},{"id":"2210.11169","title":"Content-based Graph Privacy Advisor","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2310.19582","title":"Human-interpretable and deep features for image privacy classification","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2408.04851","title":"Your Classifier Can Be Secretly a Likelihood-Based OOD Detector","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2410.07185","title":"Margin-bounded Confidence Scores for Out-of-Distribution Detection","created":"2024-09-22","cited_by_count":4,"area":null},{"id":"2412.16884","title":"Out-of-Distribution Detection with Prototypical Outlier Proxy","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2501.16718","title":"Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2507.11690","title":"The Impact of Coreset Selection on Spurious Correlations and Group Robustness","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2410.14315","title":"Optimizing importance weighting in the presence of sub-population shifts","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2603.19862","title":"IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment","created":"2026-03-20","cited_by_count":3,"area":"mllm"},{"id":"2101.04827","title":"Urban land-use analysis using proximate sensing imagery: a survey","created":"2021-01-13","cited_by_count":2,"area":null},{"id":"2303.00972","title":"Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2311.18266","title":"Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning","created":"2023-11-30","cited_by_count":2,"area":"diffusion"},{"id":"2412.01596","title":"FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2501.04150","title":"Benchmarking Large and Small MLLMs","created":"2025-01-04","cited_by_count":2,"area":"mllm"},{"id":"2501.04184","title":"MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2503.12464","title":"Learning Privacy from Visual Entities","created":"2025-03-16","cited_by_count":2,"area":null},{"id":"2507.22361","title":"Object Recognition Datasets and Challenges: A Review","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2112.12409","title":"InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2206.07326","title":"Recent Advances in Scene Image Representation and Classification","created":"2022-06-15","cited_by_count":1,"area":null},{"id":"2602.07640","title":"TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.29313","title":"HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2109.12845","title":"Bayesian deep learning of affordances from RGB images","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2208.08295","title":"ParaColorizer: Realistic Image Colorization using Parallel Generative Networks","created":"2022-08-17","cited_by_count":0,"area":null},{"id":"2210.03274","title":"TCNL: Transparent and Controllable Network Learning Via Embedding Human-Guided Concepts","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2211.04347","title":"When & How to Transfer with Transfer Learning","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2303.07402","title":"Designing Deep Networks for Scene Recognition","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2306.10397","title":"Enhancing the Prediction of Emotional Experience in Movies using Deep Neural Networks: The Significance of Audio and Language","created":"2023-06-17","cited_by_count":0,"area":null},{"id":"2310.10149","title":"Recursive Segmentation Living Image: An eXplainable AI (XAI) Approach for Computing Structural Beauty of Images or the Livingness of Space","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2405.14030","title":"Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2407.09788","title":"Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning","created":"2024-07-13","cited_by_count":0,"area":null},{"id":"2409.06183","title":"EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation","created":"2024-09-10","cited_by_count":0,"area":"diffusion"},{"id":"2411.02184","title":"Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2506.14541","title":"Exploring Diffusion with Test-Time Training on Efficient Image Restoration","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2508.03108","title":"Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.06918","title":"Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2512.11957","title":"Pre-training vision models for the classification of alerts from wide-field time-domain surveys","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2603.20186","title":"Improving Image-to-Image Translation via a Rectified Flow Reformulation","created":"2026-03-20","cited_by_count":0,"area":"diffusion"},{"id":"2603.23488","title":"One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.13142","title":"Multi-modal panoramic 3D outdoor datasets for place categorization","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.02830","title":"Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2609.37786","title":"CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals","created":"2026-09-29","cited_by_count":0,"area":"mllm"}],"next_cursor":null}