{"total":70,"rows":[{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434,"area":null},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"area":null},{"id":"2103.17230","title":"Rainbow Memory: Continual Learning with a Memory of Diverse Samples","created":"2021-03-31","cited_by_count":273,"area":null},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"area":null},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163,"area":"diffusion"},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151,"area":null},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105,"area":null},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101,"area":null},{"id":"2112.00412","title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","created":"2021-12-01","cited_by_count":100,"area":null},{"id":"2305.00729","title":"What Do Self-Supervised Vision Transformers Learn?","created":"2023-05-01","cited_by_count":93,"area":null},{"id":"2104.14754","title":"Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing","created":"2021-04-30","cited_by_count":91,"area":null},{"id":"2106.11562","title":"SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning","created":"2021-06-22","cited_by_count":71,"area":null},{"id":"2110.10031","title":"Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference","created":"2021-10-19","cited_by_count":67,"area":null},{"id":"2210.08750","title":"Keep Me Updated! Memory Management in Long-term Conversations","created":"2022-10-17","cited_by_count":63,"area":null},{"id":"2402.12974","title":"Visual Style Prompting with Swapping Self-Attention","created":"2024-02-20","cited_by_count":63,"area":"diffusion"},{"id":"2112.04487","title":"Joint Global and Local Hierarchical Priors for Learned Image Compression","created":"2021-12-08","cited_by_count":54,"area":null},{"id":"2104.00887","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","created":"2021-04-02","cited_by_count":46,"area":null},{"id":"2110.03921","title":"ViDT: An Efficient and Effective Fully Transformer-based Object Detector","created":"2021-10-08","cited_by_count":46,"area":null},{"id":"2305.18171","title":"Improved Probabilistic Image-Text Representations","created":"2023-05-29","cited_by_count":40,"area":null},{"id":"2106.08062","title":"SSMix: Saliency-Based Span Mixup for Text Classification","created":"2021-06-15","cited_by_count":39,"area":null},{"id":"2205.13445","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","created":"2022-05-25","cited_by_count":35,"area":null},{"id":"2203.15355","title":"Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries","created":"2022-03-29","cited_by_count":31,"area":null},{"id":"2406.11672","title":"Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting","created":"2024-06-17","cited_by_count":30,"area":null},{"id":"2302.13700","title":"Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech","created":"2023-02-27","cited_by_count":27,"area":"diffusion"},{"id":"2109.09477","title":"Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement","created":"2021-09-20","cited_by_count":26,"area":null},{"id":"2111.11294","title":"Scaling Law for Recommendation Models: Towards General-purpose User Representations","created":"2021-11-15","cited_by_count":26,"area":null},{"id":"2205.00176","title":"Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models","created":"2022-04-30","cited_by_count":26,"area":null},{"id":"2210.07805","title":"Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2402.04625","title":"Noise Map Guidance: Inversion with Spatial Context for Real Image Editing","created":"2024-02-07","cited_by_count":25,"area":"diffusion"},{"id":"2411.00154","title":"Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models","created":"2024-10-31","cited_by_count":24,"area":"safety"},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2302.01571","title":"Robust Camera Pose Refinement for Multi-Resolution Hash Encoding","created":"2023-02-03","cited_by_count":21,"area":null},{"id":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2105.14454","title":"NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2402.17275","title":"One-Shot Structure-Aware Stylized Image Synthesis","created":"2024-02-27","cited_by_count":14,"area":"diffusion"},{"id":"2302.06608","title":"3D-aware Blending with Generative NeRFs","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2111.02643","title":"Response Generation with Context-Aware Prompt Learning","created":"2021-11-04","cited_by_count":12,"area":null},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12,"area":null},{"id":"2112.04120","title":"Feature Statistics Mixing Regularization for Generative Adversarial Networks","created":"2021-12-08","cited_by_count":9,"area":null},{"id":"2112.14971","title":"Contrastive Fine-grained Class Clustering via Generative Adversarial Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2404.09490","title":"Leveraging Temporal Contextualization for Video Action Recognition","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2506.02362","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2207.13320","title":"Generator Knows What Discriminator Should Learn in Unconditional GANs","created":"2022-07-27","cited_by_count":7,"area":null},{"id":"2301.09091","title":"BallGAN: 3D-aware Image Synthesis with a Spherical Background","created":"2023-01-22","cited_by_count":7,"area":null},{"id":"2401.09048","title":"Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis","created":"2024-01-17","cited_by_count":7,"area":"diffusion"},{"id":"2103.00771","title":"Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning","created":"2021-03-01","cited_by_count":6,"area":null},{"id":"2510.06827","title":"StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance","created":"2025-10-08","cited_by_count":6,"area":"diffusion"},{"id":"2104.07242","title":"Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2202.02777","title":"Learning Features with Parameter-Free Layers","created":"2022-02-06","cited_by_count":5,"area":null},{"id":"2310.01400","title":"Sequential Data Generation with Groupwise Diffusion Process","created":"2023-10-02","cited_by_count":5,"area":"diffusion"},{"id":"2303.17595","title":"Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2108.10549","title":"StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures","created":"2021-08-24","cited_by_count":3,"area":null},{"id":"2204.03865","title":"Frequency Selective Augmentation for Video Representation Learning","created":"2022-04-08","cited_by_count":3,"area":null},{"id":"2207.01395","title":"Memory Efficient Patch-based Training for INR-based GANs","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2212.03760","title":"Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2403.10663","title":"Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2406.02027","title":"Inference Attacks: A Taxonomy, Survey, and Promising Directions","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2411.19067","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2110.08851","title":"Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning","created":"2021-10-17","cited_by_count":1,"area":null},{"id":"2304.04960","title":"Panoramic Image-to-Image Translation","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2402.10403","title":"Polyhedral Complex Derivation from Piecewise Trilinear Networks","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2505.19821","title":"Poison in the Well: Feature Embedding Disruption in Backdoor Attacks","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2102.00441","title":"M2FN: Multi-step Modality Fusion for Advertisement Image Assessment","created":"2021-01-31","cited_by_count":0,"area":null},{"id":"2511.16273","title":"TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.21098","title":"Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction","created":"2025-11-26","cited_by_count":0,"area":null}],"next_cursor":null}