{"total":84,"rows":[{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"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":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50,"area":null},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2304.00946","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","created":"2023-04-03","cited_by_count":37,"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":"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,"area":null},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31,"area":null},{"id":"2207.06580","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","created":"2022-07-14","cited_by_count":29,"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":"2206.04790","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","created":"2022-06-09","cited_by_count":27,"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":"2405.02077","title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","created":"2024-05-03","cited_by_count":25,"area":null},{"id":"2203.11378","title":"HyperShot: Few-Shot Learning by Kernel HyperNetworks","created":"2022-03-21","cited_by_count":24,"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":"2207.08677","title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","created":"2022-07-18","cited_by_count":23,"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":"2211.00005","title":"Uncertainty-DTW for Time Series and Sequences","created":"2022-10-30","cited_by_count":21,"area":null},{"id":"2110.12358","title":"A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark","created":"2021-10-24","cited_by_count":16,"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":"2107.13029","title":"A New Split for Evaluating True Zero-Shot Action Recognition","created":"2021-07-27","cited_by_count":14,"area":null},{"id":"2202.11423","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","created":"2022-02-23","cited_by_count":13,"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":"2212.04873","title":"Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition","created":"2022-12-09","cited_by_count":13,"area":null},{"id":"2301.03330","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","created":"2023-01-09","cited_by_count":12,"area":null},{"id":"2402.03019","title":"Taylor Videos for Action Recognition","created":"2024-02-05","cited_by_count":12,"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":"2407.14744","title":"A Comprehensive Review of Few-shot Action Recognition","created":"2024-07-20","cited_by_count":11,"area":null},{"id":"2208.09424","title":"Hierarchical Compositional Representations for Few-shot Action Recognition","created":"2022-08-19","cited_by_count":10,"area":null},{"id":"2407.18249","title":"Trajectory-aligned Space-time Tokens for Few-shot Action Recognition","created":"2024-07-25","cited_by_count":10,"area":null},{"id":"2408.12475","title":"Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition","created":"2024-08-22","cited_by_count":10,"area":null},{"id":"2504.05956","title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2207.09759","title":"Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9,"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":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"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,"area":null},{"id":"2108.06647","title":"Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","created":"2021-08-15","cited_by_count":7,"area":null},{"id":"2303.10451","title":"Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2305.06114","title":"Few-shot Action Recognition via Intra- and Inter-Video Information Maximization","created":"2023-05-10","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":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2508.03695","title":"Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition","created":"2025-08-05","cited_by_count":7,"area":null},{"id":"2211.12030","title":"Knowledge Prompting for Few-shot Action Recognition","created":"2022-11-22","cited_by_count":6,"area":"mllm"},{"id":"2511.12878","title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2308.01532","title":"MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition","created":"2023-08-03","cited_by_count":4,"area":"mllm"},{"id":"2309.17327","title":"Telling Stories for Common Sense Zero-Shot Action Recognition","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2312.01083","title":"Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CP$\\mathbf{M^2}$C)","created":"2023-12-02","cited_by_count":4,"area":null},{"id":"2402.12706","title":"Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2407.05657","title":"DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2602.18043","title":"Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2212.01638","title":"VLG: General Video Recognition with Web Textual Knowledge","created":"2022-12-03","cited_by_count":3,"area":null},{"id":"2305.08420","title":"Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2307.01985","title":"Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2401.08345","title":"Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-$\\mathrm{M^2}$DF)","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2406.01073","title":"Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2412.07481","title":"Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence","created":"2024-12-10","cited_by_count":2,"area":"ssm"},{"id":"2502.12582","title":"Adaptive Prototype Model for Attribute-based Multi-label Few-shot Action Recognition","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.14430","title":"Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2507.16287","title":"Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2106.11173","title":"TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2309.03869","title":"Text-to-feature diffusion for audio-visual few-shot learning","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2312.01431","title":"D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition","created":"2023-12-03","cited_by_count":1,"area":null},{"id":"2407.16344","title":"SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2503.00276","title":"Learning to Animate Images from A Few Videos to Portray Delicate Human Actions","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2510.09203","title":"Cattle-CLIP: A Multimodal Framework for Cattle Behaviour Recognition from Video","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2204.08874","title":"Less than Few: Self-Shot Video Instance Segmentation","created":"2022-04-19","cited_by_count":0,"area":null},{"id":"2303.16084","title":"Rethinking matching-based few-shot action recognition","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2403.14362","title":"Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2408.04243","title":"MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2411.11335","title":"Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2504.10079","title":"Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2505.06002","title":"Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2506.13322","title":"Active Multimodal Distillation for Few-shot Action Recognition","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2509.17638","title":"A$^2$M$^2$-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2511.06741","title":"Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2511.18711","title":"Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.11340","title":"Task-Specific Distance Correlation Matching for Few-Shot Action Recognition","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2603.04125","title":"A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.26033","title":"Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs","created":"2026-03-27","cited_by_count":0,"area":"mllm"},{"id":"2605.13202","title":"STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition","created":"2026-05-13","cited_by_count":0,"area":"ssm"},{"id":"2609.05242","title":"Few-Shot Video Recognition via Hierarchical Metric Learning","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.18209","title":"Closing the Estimation Gap: Training-Free Transductive Inference for Cross-Domain Few-Shot Action Recognition","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}