{"total":203,"rows":[{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176,"area":null},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112,"area":null},{"id":"2302.00864","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","created":"2023-02-02","cited_by_count":96,"area":null},{"id":"2103.16173","title":"Contrastive Embedding for Generalized Zero-Shot Learning","created":"2021-03-30","cited_by_count":94,"area":null},{"id":"2201.01490","title":"Debiased Learning from Naturally Imbalanced Pseudo-Labels","created":"2022-01-05","cited_by_count":85,"area":null},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79,"area":null},{"id":"2202.06671","title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","created":"2022-02-14","cited_by_count":75,"area":null},{"id":"2303.12311","title":"Frozen Language Model Helps ECG Zero-Shot Learning","created":"2023-03-22","cited_by_count":62,"area":null},{"id":"2102.01645","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","created":"2021-02-02","cited_by_count":57,"area":null},{"id":"2110.07059","title":"Subspace Regularizers for Few-Shot Class Incremental Learning","created":"2021-10-13","cited_by_count":56,"area":null},{"id":"2108.06230","title":"Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds","created":"2021-08-13","cited_by_count":55,"area":null},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54,"area":null},{"id":"2212.02291","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","created":"2022-12-05","cited_by_count":54,"area":null},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50,"area":null},{"id":"2105.01017","title":"Learning Graph Embeddings for Open World Compositional Zero-Shot Learning","created":"2021-05-03","cited_by_count":49,"area":null},{"id":"2308.15827","title":"Introducing Language Guidance in Prompt-based Continual Learning","created":"2023-08-30","cited_by_count":49,"area":null},{"id":"2206.00423","title":"Open-environment Machine Learning","created":"2022-06-01","cited_by_count":48,"area":null},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2103.00070","title":"Knowledge-aware Zero-Shot Learning: Survey and Perspective","created":"2021-02-26","cited_by_count":41,"area":null},{"id":"2108.12517","title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","created":"2021-08-27","cited_by_count":41,"area":null},{"id":"2207.00691","title":"American == White in Multimodal Language-and-Image AI","created":"2022-07-01","cited_by_count":39,"area":null},{"id":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36,"area":null},{"id":"2107.13782","title":"Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions","created":"2021-07-29","cited_by_count":35,"area":null},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2205.10764","title":"Evidence for Hypodescent in Visual Semantic AI","created":"2022-05-22","cited_by_count":30,"area":null},{"id":"2102.12152","title":"Dual-Awareness Attention for Few-Shot Object Detection","created":"2021-02-24","cited_by_count":29,"area":null},{"id":"2205.11378","title":"Markedness in Visual Semantic AI","created":"2022-05-23","cited_by_count":29,"area":null},{"id":"2303.15111","title":"Learning Attention as Disentangler for Compositional Zero-shot Learning","created":"2023-03-27","cited_by_count":29,"area":null},{"id":"2203.10444","title":"VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning","created":"2022-03-20","cited_by_count":27,"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":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2109.06062","title":"Semantics-Guided Contrastive Network for Zero-Shot Object detection","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2111.02073","title":"Dual Progressive Prototype Network for Generalized Zero-Shot Learning","created":"2021-11-03","cited_by_count":26,"area":null},{"id":"2203.05061","title":"HealthPrompt: A Zero-shot Learning Paradigm for Clinical Natural Language Processing","created":"2022-03-09","cited_by_count":26,"area":null},{"id":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","cited_by_count":25,"area":null},{"id":"2101.11530","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","created":"2021-01-27","cited_by_count":24,"area":null},{"id":"2303.15322","title":"Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning","created":"2023-03-27","cited_by_count":24,"area":null},{"id":"2106.13058","title":"Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design","created":"2021-06-24","cited_by_count":23,"area":null},{"id":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23,"area":null},{"id":"2102.02925","title":"Generalized Zero-shot Intent Detection via Commonsense Knowledge","created":"2021-02-04","cited_by_count":21,"area":null},{"id":"2203.03483","title":"Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention","created":"2022-03-07","cited_by_count":21,"area":null},{"id":"2312.04076","title":"Large Language Models are Good Prompt Learners for Low-Shot Image Classification","created":"2023-12-07","cited_by_count":21,"area":null},{"id":"2102.11115","title":"Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case","created":"2021-02-22","cited_by_count":20,"area":null},{"id":"2108.01828","title":"Emergent Discrete Communication in Semantic Spaces","created":"2021-08-04","cited_by_count":20,"area":null},{"id":"2109.14133","title":"Fine-Grained Zero-Shot Learning with DNA as Side Information","created":"2021-09-29","cited_by_count":20,"area":null},{"id":"2112.13884","title":"A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision","created":"2021-12-27","cited_by_count":19,"area":null},{"id":"2102.02038","title":"Isometric Propagation Network for Generalized Zero-shot Learning","created":"2021-02-03","cited_by_count":18,"area":null},{"id":"2111.14673","title":"3D Compositional Zero-shot Learning with DeCompositional Consensus","created":"2021-11-29","cited_by_count":16,"area":null},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","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":"2305.13173","title":"Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2308.04828","title":"Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning","created":"2023-08-09","cited_by_count":16,"area":null},{"id":"2103.16597","title":"Rectification-based Knowledge Retention for Continual Learning","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2311.00277","title":"OpenForest: A data catalogue for machine learning in forest monitoring","created":"2023-11-01","cited_by_count":15,"area":null},{"id":"2106.04530","title":"Learning from Multiple Noisy Partial Labelers","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2212.00784","title":"Improving Zero-Shot Models with Label Distribution Priors","created":"2022-12-01","cited_by_count":14,"area":null},{"id":"2304.02846","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","created":"2023-04-06","cited_by_count":14,"area":null},{"id":"2209.06701","title":"Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora","created":"2022-09-14","cited_by_count":13,"area":null},{"id":"2106.00264","title":"Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning","created":"2021-06-01","cited_by_count":12,"area":null},{"id":"2102.04680","title":"Tr\\\"aumerAI: Dreaming Music with StyleGAN","created":"2021-02-09","cited_by_count":11,"area":null},{"id":"2204.04601","title":"Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention","created":"2022-04-10","cited_by_count":11,"area":null},{"id":"2504.13822","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2105.04881","title":"Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review","created":"2021-05-11","cited_by_count":10,"area":null},{"id":"2106.06360","title":"Conterfactual Generative Zero-Shot Semantic Segmentation","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2106.06410","title":"What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2207.10150","title":"Tackling Long-Tailed Category Distribution Under Domain Shifts","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2104.10355","title":"Revisiting Document Representations for Large-Scale Zero-Shot Learning","created":"2021-04-21","cited_by_count":9,"area":null},{"id":"2206.03318","title":"LegoNN: Building Modular Encoder-Decoder Models","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2210.02771","title":"Modelling Commonsense Properties using Pre-Trained Bi-Encoders","created":"2022-10-06","cited_by_count":9,"area":null},{"id":"2302.04723","title":"Zero-Shot Learning for Requirements Classification: An Exploratory Study","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2102.08747","title":"Learning Visual Models using a Knowledge Graph as a Trainer","created":"2021-02-17","cited_by_count":8,"area":null},{"id":"2202.10680","title":"Submodlib: A Submodular Optimization Library","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2202.11917","title":"Machine Learning for Intrusion Detection in Industrial Control Systems: Applications, Challenges, and Recommendations","created":"2022-02-24","cited_by_count":8,"area":null},{"id":"2203.12274","title":"Pre-training to Match for Unified Low-shot Relation Extraction","created":"2022-03-23","cited_by_count":8,"area":null},{"id":"2305.09785","title":"Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models","created":"2023-05-16","cited_by_count":8,"area":null},{"id":"2309.00923","title":"GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning","created":"2023-09-02","cited_by_count":8,"area":null},{"id":"2405.19532","title":"Contrasting Multiple Representations with the Multi-Marginal Matching Gap","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2101.08894","title":"Generative Replay-based Continual Zero-Shot Learning","created":"2021-01-22","cited_by_count":7,"area":null},{"id":"2103.12347","title":"Shared Latent Space of Font Shapes and Their Noisy Impressions","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2111.03651","title":"The Curious Layperson: Fine-Grained Image Recognition without Expert Labels","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2201.01337","title":"ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling","created":"2022-01-04","cited_by_count":7,"area":null},{"id":"2201.11794","title":"A Survey on Visual Transfer Learning using Knowledge Graphs","created":"2022-01-27","cited_by_count":7,"area":null},{"id":"2305.16681","title":"CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2101.00173","title":"CIZSL++: Creativity Inspired Generative Zero-Shot Learning","created":"2021-01-01","cited_by_count":6,"area":null},{"id":"2110.07130","title":"Region Semantically Aligned Network for Zero-Shot Learning","created":"2021-10-14","cited_by_count":6,"area":null},{"id":"2201.10972","title":"How Robust are Discriminatively Trained Zero-Shot Learning Models?","created":"2022-01-26","cited_by_count":6,"area":null},{"id":"2203.04195","title":"A Gating Model for Bias Calibration in Generalized Zero-shot Learning","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2206.02179","title":"A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism","created":"2022-06-05","cited_by_count":6,"area":null},{"id":"2207.03133","title":"Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions","created":"2022-07-07","cited_by_count":6,"area":null},{"id":"2308.09915","title":"EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning","created":"2023-08-19","cited_by_count":6,"area":null},{"id":"2307.12226","title":"Geometry-Aware Adaptation for Pretrained Models","created":"2023-07-23","cited_by_count":5,"area":null},{"id":"2310.09821","title":"LICO: Explainable Models with Language-Image Consistency","created":"2023-10-15","cited_by_count":5,"area":null},{"id":"2311.01373","title":"Recognize Any Regions","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2404.05667","title":"AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation","created":"2024-04-08","cited_by_count":5,"area":null}],"next_cursor":"100"}