{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2403.20320","title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","created":"2024-03-29","cited_by_count":44},{"id":"2504.16053","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","created":"2025-04-22","cited_by_count":42},{"id":"2211.12764","title":"VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval","created":"2022-11-23","cited_by_count":36},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34},{"id":"2402.02382","title":"Revisiting the Power of Prompt for Visual Tuning","created":"2024-02-04","cited_by_count":32},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30},{"id":"2310.08381","title":"AutoVP: An Automated Visual Prompting Framework and Benchmark","created":"2023-10-12","cited_by_count":29},{"id":"2401.10588","title":"DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval","created":"2024-01-19","cited_by_count":26},{"id":"2406.06820","title":"Adapters Strike Back","created":"2024-06-10","cited_by_count":16},{"id":"2503.15973","title":"STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding","created":"2025-03-20","cited_by_count":13},{"id":"2505.04575","title":"Componential Prompt-Knowledge Alignment for Domain Incremental Learning","created":"2025-05-07","cited_by_count":13},{"id":"2412.09224","title":"DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification","created":"2024-12-12","cited_by_count":12},{"id":"2503.12866","title":"SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting","created":"2025-03-17","cited_by_count":12},{"id":"2405.16504","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","created":"2024-05-26","cited_by_count":11},{"id":"2411.03855","title":"MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba","created":"2024-11-06","cited_by_count":11},{"id":"2507.01884","title":"Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification","created":"2025-07-02","cited_by_count":7},{"id":"2412.08947","title":"Selective Visual Prompting in Vision Mamba","created":"2024-12-12","cited_by_count":6},{"id":"2411.15224","title":"Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation","created":"2024-11-21","cited_by_count":4}],"next_cursor":null}