{"total":174,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"area":null},{"id":"2204.07305","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","created":"2022-04-15","cited_by_count":126,"area":null},{"id":"2112.10740","title":"Are Large-scale Datasets Necessary for Self-Supervised Pre-training?","created":"2021-12-20","cited_by_count":117,"area":null},{"id":"2107.03358","title":"Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation","created":"2021-07-07","cited_by_count":104,"area":"distill"},{"id":"2304.03410","title":"$R^{2}$Former: Unified $R$etrieval and $R$eranking Transformer for Place Recognition","created":"2023-04-06","cited_by_count":102,"area":null},{"id":"2207.11549","title":"Self-Support Few-Shot Semantic Segmentation","created":"2022-07-23","cited_by_count":96,"area":null},{"id":"2110.06976","title":"Representational Continuity for Unsupervised Continual Learning","created":"2021-10-13","cited_by_count":95,"area":null},{"id":"2112.09581","title":"Watermarking Images in Self-Supervised Latent Spaces","created":"2021-12-17","cited_by_count":94,"area":null},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84,"area":null},{"id":"2107.00358","title":"Cross-domain Few-shot Learning with Task-specific Adapters","created":"2021-07-01","cited_by_count":80,"area":null},{"id":"2108.09666","title":"Relational Embedding for Few-Shot Classification","created":"2021-08-22","cited_by_count":74,"area":null},{"id":"2203.15021","title":"Few-Shot Object Detection with Fully Cross-Transformer","created":"2022-03-28","cited_by_count":64,"area":null},{"id":"2204.13861","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","created":"2022-04-29","cited_by_count":58,"area":null},{"id":"2103.01315","title":"Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning","created":"2021-03-01","cited_by_count":56,"area":null},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56,"area":null},{"id":"2112.05132","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","created":"2021-12-09","cited_by_count":53,"area":null},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52,"area":null},{"id":"2107.07746","title":"Rectifying the Shortcut Learning of Background for Few-Shot Learning","created":"2021-07-16","cited_by_count":51,"area":null},{"id":"2204.04567","title":"Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification","created":"2022-04-09","cited_by_count":50,"area":null},{"id":"2301.12246","title":"A Closer Look at Few-shot Classification Again","created":"2023-01-28","cited_by_count":46,"area":null},{"id":"2112.05749","title":"Label, Verify, Correct: A Simple Few Shot Object Detection Method","created":"2021-12-10","cited_by_count":43,"area":null},{"id":"2206.07267","title":"Rethinking Generalization in Few-Shot Classification","created":"2022-06-15","cited_by_count":36,"area":null},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35,"area":null},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33,"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":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2112.03243","title":"Input-level Inductive Biases for 3D Reconstruction","created":"2021-12-06","cited_by_count":31,"area":null},{"id":"2209.08224","title":"Few-Shot Classification with Contrastive Learning","created":"2022-09-17","cited_by_count":31,"area":null},{"id":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2204.00949","title":"Matching Feature Sets for Few-Shot Image Classification","created":"2022-04-02","cited_by_count":25,"area":null},{"id":"2303.14348","title":"Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style","created":"2023-03-25","cited_by_count":25,"area":null},{"id":"2306.08713","title":"What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2308.09346","title":"Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching","created":"2023-08-18","cited_by_count":24,"area":null},{"id":"2105.08149","title":"Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments","created":"2021-05-17","cited_by_count":23,"area":null},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23,"area":null},{"id":"2204.05494","title":"Few-shot Learning with Noisy Labels","created":"2022-04-12","cited_by_count":23,"area":null},{"id":"2207.08677","title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","created":"2022-07-18","cited_by_count":23,"area":null},{"id":"2209.00517","title":"The Neural Process Family: Survey, Applications and Perspectives","created":"2022-09-01","cited_by_count":23,"area":null},{"id":"2303.15466","title":"Supervised Masked Knowledge Distillation for Few-Shot Transformers","created":"2023-03-25","cited_by_count":23,"area":"distill"},{"id":"2203.07057","title":"Self-Promoted Supervision for Few-Shot Transformer","created":"2022-03-14","cited_by_count":22,"area":null},{"id":"2304.01143","title":"Use Your Head: Improving Long-Tail Video Recognition","created":"2023-04-03","cited_by_count":22,"area":null},{"id":"2109.04898","title":"LibFewShot: A Comprehensive Library for Few-shot Learning","created":"2021-09-10","cited_by_count":21,"area":null},{"id":"2207.01376","title":"Task Discrepancy Maximization for Fine-grained Few-Shot Classification","created":"2022-07-04","cited_by_count":21,"area":null},{"id":"2303.15591","title":"Learning Expressive Prompting With Residuals for Vision Transformers","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2206.08126","title":"Channel Importance Matters in Few-Shot Image Classification","created":"2022-06-16","cited_by_count":20,"area":null},{"id":"2106.05517","title":"Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification","created":"2021-06-10","cited_by_count":18,"area":null},{"id":"2104.02638","title":"Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark","created":"2021-04-06","cited_by_count":16,"area":null},{"id":"2208.12398","title":"Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification","created":"2022-08-26","cited_by_count":16,"area":null},{"id":"2301.02419","title":"Exploring Efficient Few-shot Adaptation for Vision Transformers","created":"2023-01-06","cited_by_count":16,"area":null},{"id":"2110.05076","title":"A Closer Look at Prototype Classifier for Few-shot Image Classification","created":"2021-10-11","cited_by_count":15,"area":null},{"id":"2112.01719","title":"Adaptive Poincar\\'e Point to Set Distance for Few-Shot Classification","created":"2021-12-03","cited_by_count":15,"area":null},{"id":"2206.04679","title":"POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15,"area":null},{"id":"2311.18649","title":"Simple Semantic-Aided Few-Shot Learning","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2107.01105","title":"Memory Efficient Meta-Learning with Large Images","created":"2021-07-02","cited_by_count":14,"area":null},{"id":"2109.09883","title":"On the Importance of Distractors for Few-Shot Classification","created":"2021-09-20","cited_by_count":14,"area":null},{"id":"2109.12932","title":"Sparse Spatial Transformers for Few-Shot Learning","created":"2021-09-27","cited_by_count":14,"area":null},{"id":"2203.09093","title":"Semantic-aligned Fusion Transformer for One-shot Object Detection","created":"2022-03-17","cited_by_count":13,"area":null},{"id":"2208.13474","title":"Prompt Tuning with Soft Context Sharing for Vision-Language Models","created":"2022-08-29","cited_by_count":13,"area":"mllm"},{"id":"2212.04873","title":"Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition","created":"2022-12-09","cited_by_count":13,"area":null},{"id":"2109.12548","title":"Disentangled Feature Representation for Few-shot Image Classification","created":"2021-09-26","cited_by_count":12,"area":null},{"id":"2211.14782","title":"Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection","created":"2022-11-27","cited_by_count":12,"area":null},{"id":"2211.17161","title":"Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification","created":"2022-11-30","cited_by_count":12,"area":null},{"id":"2307.03073","title":"Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning","created":"2023-07-06","cited_by_count":12,"area":"mllm"},{"id":"2103.14341","title":"MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning","created":"2021-03-26","cited_by_count":11,"area":null},{"id":"2109.15317","title":"Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation","created":"2021-09-30","cited_by_count":11,"area":null},{"id":"2203.03978","title":"Contrastive Conditional Neural Processes","created":"2022-03-08","cited_by_count":11,"area":null},{"id":"2204.07841","title":"Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting","created":"2022-04-16","cited_by_count":11,"area":null},{"id":"2308.07119","title":"On the Importance of Spatial Relations for Few-shot Action Recognition","created":"2023-08-14","cited_by_count":11,"area":null},{"id":"2401.02746","title":"Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2404.04452","title":"Vision transformers in domain adaptation and domain generalization: a study of robustness","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2202.08391","title":"Graph Masked Autoencoders with Transformers","created":"2022-02-17","cited_by_count":10,"area":null},{"id":"2303.18210","title":"A Closer Look at Few-Shot 3D Point Cloud Classification","created":"2023-03-31","cited_by_count":10,"area":null},{"id":"2310.03843","title":"From Channel Bias to Feature Redundancy: Uncovering the \"Less is More\" Principle in Few-Shot Learning","created":"2023-10-05","cited_by_count":10,"area":null},{"id":"2103.08160","title":"DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network","created":"2021-03-15","cited_by_count":9,"area":null},{"id":"2111.14576","title":"Recurrent Vision Transformer for Solving Visual Reasoning Problems","created":"2021-11-29","cited_by_count":9,"area":null},{"id":"2203.13465","title":"CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification","created":"2022-03-25","cited_by_count":9,"area":null},{"id":"2207.00784","title":"Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification","created":"2022-07-02","cited_by_count":9,"area":null},{"id":"2210.04485","title":"A Memory Transformer Network for Incremental Learning","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2103.16009","title":"Revisiting Local Descriptor for Improved Few-Shot Classification","created":"2021-03-30","cited_by_count":8,"area":null},{"id":"2105.11874","title":"Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images","created":"2021-05-25","cited_by_count":8,"area":null},{"id":"2106.07550","title":"Attention mechanisms and deep learning for machine vision: A survey of the state of the art","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2112.04585","title":"MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification","created":"2021-12-08","cited_by_count":8,"area":null},{"id":"2204.03749","title":"Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2207.03333","title":"FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments","created":"2022-07-06","cited_by_count":8,"area":null},{"id":"2212.04884","title":"Co-training $2^L$ Submodels for Visual Recognition","created":"2022-12-09","cited_by_count":8,"area":"distill"},{"id":"2307.14612","title":"GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2108.05010","title":"Prototype Completion for Few-Shot Learning","created":"2021-08-11","cited_by_count":7,"area":null},{"id":"2311.06218","title":"Semantic-aware Video Representation for Few-shot Action Recognition","created":"2023-11-10","cited_by_count":7,"area":null},{"id":"2312.15894","title":"Task-Disruptive Background Suppression for Few-Shot Segmentation","created":"2023-12-26","cited_by_count":7,"area":null},{"id":"2401.13987","title":"Cross-Domain Few-Shot Learning via Adaptive Transformer Networks","created":"2024-01-25","cited_by_count":7,"area":null},{"id":"2403.04492","title":"Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2509.25033","title":"VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2101.11058","title":"Supervised Momentum Contrastive Learning for Few-Shot Classification","created":"2021-01-26","cited_by_count":6,"area":null},{"id":"2211.00868","title":"tSF: Transformer-based Semantic Filter for Few-Shot Learning","created":"2022-11-02","cited_by_count":6,"area":null}],"next_cursor":"100"}