{"list":"other","total":60,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"2003.13193","title":"Adversarial Feature Hallucination Networks for Few-Shot Learning","created":"2020-03-30","cited_by_count":110},{"id":"1905.11116","title":"Finding Task-Relevant Features for Few-Shot Learning by Category Traversal","created":"2019-05-27","cited_by_count":101},{"id":"1902.07104","title":"Adaptive Cross-Modal Few-Shot Learning","created":"2019-02-19","cited_by_count":95},{"id":"1709.01643","title":"Learning to Compose Domain-Specific Transformations for Data Augmentation","created":"2017-09-06","cited_by_count":91},{"id":"1905.06549","title":"TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","created":"2019-05-16","cited_by_count":91},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"1804.05298","title":"Multi-level Semantic Feature Augmentation for One-shot Learning","created":"2018-04-15","cited_by_count":62},{"id":"1905.11641","title":"Image Deformation Meta-Networks for One-Shot Learning","created":"2019-05-28","cited_by_count":56},{"id":"2112.05132","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","created":"2021-12-09","cited_by_count":53},{"id":"2010.09982","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","created":"2020-10-20","cited_by_count":50},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50},{"id":"1909.13245","title":"Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction","created":"2019-09-29","cited_by_count":47},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41},{"id":"2205.02918","title":"Generating Representative Samples for Few-Shot Classification","created":"2022-05-05","cited_by_count":39},{"id":"2304.00946","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","created":"2023-04-03","cited_by_count":37},{"id":"1811.00270","title":"Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition","created":"2018-11-01","cited_by_count":36},{"id":"2107.04782","title":"TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition","created":"2021-07-10","cited_by_count":35},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34},{"id":"1906.02944","title":"Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning","created":"2019-06-07","cited_by_count":29},{"id":"2303.14123","title":"Semantic Prompt for Few-Shot Image Recognition","created":"2023-03-24","cited_by_count":29},{"id":"2405.02077","title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","created":"2024-05-03","cited_by_count":25},{"id":"2308.09346","title":"Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching","created":"2023-08-18","cited_by_count":24},{"id":"2207.10785","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","created":"2022-07-21","cited_by_count":23},{"id":"2404.04308","title":"Visual Knowledge in the Big Model Era: Retrospect and Prospect","created":"2024-04-05","cited_by_count":16},{"id":"2112.01037","title":"Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention","created":"2021-12-02","cited_by_count":15},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15},{"id":"2311.18649","title":"Simple Semantic-Aided Few-Shot Learning","created":"2023-11-30","cited_by_count":15},{"id":"2502.06501","title":"Learning Clustering-based Prototypes for Compositional Zero-shot Learning","created":"2025-02-10","cited_by_count":14},{"id":"2210.00132","title":"Alignment-guided Temporal Attention for Video Action Recognition","created":"2022-09-30","cited_by_count":10},{"id":"2504.05956","title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","created":"2025-04-08","cited_by_count":10},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9},{"id":"2408.00249","title":"Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition","created":"2024-08-01","cited_by_count":8},{"id":"2308.01532","title":"MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition","created":"2023-08-03","cited_by_count":4},{"id":"2212.01638","title":"VLG: General Video Recognition with Web Textual Knowledge","created":"2022-12-03","cited_by_count":3}],"next_cursor":null}