{"total":135,"rows":[{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906,"area":"distill"},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199,"area":"mllm"},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150,"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":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119,"area":"mllm"},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102,"area":null},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91,"area":null},{"id":"2201.01490","title":"Debiased Learning from Naturally Imbalanced Pseudo-Labels","created":"2022-01-05","cited_by_count":85,"area":null},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79,"area":null},{"id":"2203.10593","title":"Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation","created":"2022-03-20","cited_by_count":68,"area":"distill"},{"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":"2108.06536","title":"Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation","created":"2021-08-14","cited_by_count":53,"area":null},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50,"area":null},{"id":"2108.05137","title":"Zero-Shot Day-Night Domain Adaptation with a Physics Prior","created":"2021-08-11","cited_by_count":47,"area":null},{"id":"2104.04697","title":"ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning","created":"2021-04-10","cited_by_count":46,"area":null},{"id":"2102.07339","title":"OntoZSL: Ontology-enhanced Zero-shot Learning","created":"2021-02-15","cited_by_count":45,"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":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","cited_by_count":38,"area":null},{"id":"2112.09445","title":"Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation","created":"2021-12-17","cited_by_count":36,"area":null},{"id":"2312.01044","title":"Large Language Models Are Zero-Shot Text Classifiers","created":"2023-12-02","cited_by_count":35,"area":null},{"id":"2309.00775","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","created":"2023-09-02","cited_by_count":31,"area":null},{"id":"2112.08643","title":"TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2108.09301","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","created":"2021-08-20","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":"2109.06062","title":"Semantics-Guided Contrastive Network for Zero-Shot Object detection","created":"2021-09-04","cited_by_count":26,"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":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24,"area":null},{"id":"2308.00313","title":"Zero-Shot Learning by Harnessing Adversarial Samples","created":"2023-08-01","cited_by_count":24,"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":"2104.08945","title":"Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation","created":"2021-04-18","cited_by_count":22,"area":"distill"},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22,"area":null},{"id":"2203.01386","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","created":"2022-03-02","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":"2307.10782","title":"See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data","created":"2023-07-20","cited_by_count":21,"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":"2203.15310","title":"Hybrid Routing Transformer for Zero-Shot Learning","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2101.11606","title":"Generative Multi-Label Zero-Shot Learning","created":"2021-01-27","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":"2308.10599","title":"Image-free Classifier Injection for Zero-Shot Classification","created":"2023-08-21","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":"2303.05689","title":"Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity","created":"2023-03-10","cited_by_count":13,"area":null},{"id":"2108.00045","title":"Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning","created":"2021-07-30","cited_by_count":12,"area":null},{"id":"2204.10760","title":"iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition","created":"2022-04-22","cited_by_count":12,"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":"2104.10355","title":"Revisiting Document Representations for Large-Scale Zero-Shot Learning","created":"2021-04-21","cited_by_count":9,"area":null},{"id":"2104.11934","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","created":"2021-04-24","cited_by_count":9,"area":null},{"id":"2101.03292","title":"Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning","created":"2021-01-09","cited_by_count":8,"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":"2109.04378","title":"Dynamic Modeling of Hand-Object Interactions via Tactile Sensing","created":"2021-09-09","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":"2101.08894","title":"Generative Replay-based Continual Zero-Shot Learning","created":"2021-01-22","cited_by_count":7,"area":null},{"id":"2106.01487","title":"LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes","created":"2021-06-02","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":"2303.08698","title":"Bi-directional Distribution Alignment for Transductive Zero-Shot Learning","created":"2023-03-15","cited_by_count":7,"area":null},{"id":"2405.05714","title":"Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning","created":"2024-05-08","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":"2106.15047","title":"Benchmarking Knowledge-driven Zero-shot Learning","created":"2021-06-29","cited_by_count":6,"area":null},{"id":"2108.13592","title":"Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systems","created":"2021-08-31","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":"2207.01708","title":"Disentangled Action Recognition with Knowledge Bases","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2208.09562","title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","created":"2022-08-19","cited_by_count":6,"area":null},{"id":"2310.04689","title":"SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection","created":"2023-10-07","cited_by_count":6,"area":"diffusion"},{"id":"2503.10252","title":"SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2110.00860","title":"Implicit and Explicit Attention for Zero-Shot Learning","created":"2021-10-02","cited_by_count":5,"area":null},{"id":"2307.12226","title":"Geometry-Aware Adaptation for Pretrained Models","created":"2023-07-23","cited_by_count":5,"area":null},{"id":"2108.10967","title":"Field-Guide-Inspired Zero-Shot Learning","created":"2021-08-24","cited_by_count":4,"area":null},{"id":"2209.01994","title":"Federated Zero-Shot Learning for Visual Recognition","created":"2022-09-05","cited_by_count":4,"area":"safety"},{"id":"2211.01292","title":"Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2211.03252","title":"Zero-Shot Classification by Logical Reasoning on Natural Language Explanations","created":"2022-11-07","cited_by_count":4,"area":"lr"},{"id":"2301.00998","title":"Vocabulary-informed Zero-shot and Open-set Learning","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2403.09363","title":"Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2502.09018","title":"Zero-shot Concept Bottleneck Models","created":"2025-02-13","cited_by_count":4,"area":null},{"id":"2510.13675","title":"Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2103.05132","title":"AfriVEC: Word Embedding Models for African Languages. Case Study of Fon and Nobiin","created":"2021-03-08","cited_by_count":3,"area":null},{"id":"2103.10741","title":"Online Lifelong Generalized Zero-Shot Learning","created":"2021-03-19","cited_by_count":3,"area":"distill"},{"id":"2105.03164","title":"Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification","created":"2021-05-07","cited_by_count":3,"area":null},{"id":"2306.14628","title":"An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning","created":"2023-06-26","cited_by_count":3,"area":"mechinterp"},{"id":"2309.11710","title":"ContextRef: Evaluating Referenceless Metrics For Image Description Generation","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2312.01167","title":"Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning","created":"2023-12-02","cited_by_count":3,"area":null},{"id":"2402.09242","title":"Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2405.15289","title":"Learning Invariant Causal Mechanism from Vision-Language Models","created":"2024-05-24","cited_by_count":3,"area":"mllm"},{"id":"2408.12253","title":"Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2410.11560","title":"PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2511.08170","title":"Distributed Zero-Shot Learning for Visual Recognition","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2603.28211","title":"Explaining CLIP Zero-shot Predictions Through Concepts","created":"2026-03-30","cited_by_count":3,"area":"mllm"},{"id":"2102.11856","title":"Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2104.09757","title":"Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2104.09967","title":"Multi-target prediction for dummies using two-branch neural networks","created":"2021-04-19","cited_by_count":2,"area":null},{"id":"2105.11789","title":"GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition","created":"2021-05-25","cited_by_count":2,"area":null},{"id":"2201.01823","title":"Learning Semantic Ambiguities for Zero-Shot Learning","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2202.11319","title":"Absolute Zero-Shot Learning","created":"2022-02-23","cited_by_count":2,"area":null},{"id":"2210.06120","title":"Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2212.06097","title":"Resolving Semantic Confusions for Improved Zero-Shot Detection","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2212.13151","title":"Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning","created":"2022-12-26","cited_by_count":2,"area":null},{"id":"2404.06309","title":"Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models","created":"2024-04-09","cited_by_count":2,"area":"mllm"},{"id":"2507.22791","title":"Modality-Aware Feature Matching in Visual and Vision-Language Applications: A Comprehensive Survey","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2102.03137","title":"Zero-shot Learning with Deep Neural Networks for Object Recognition","created":"2021-02-05","cited_by_count":1,"area":null}],"next_cursor":"100"}