{"list":"other","total":63,"rows":[{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"id":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84},{"id":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83},{"id":"2407.15138","title":"D$^4$M: Dataset Distillation via Disentangled Diffusion Model","created":"2024-07-21","cited_by_count":77},{"id":"2311.17950","title":"Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching","created":"2023-11-29","cited_by_count":69},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46},{"id":"2502.20653","title":"Dataset Distillation with Neural Characteristic Function: A Minmax Perspective","created":"2025-02-28","cited_by_count":45},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40},{"id":"2409.17612","title":"Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment","created":"2024-09-26","cited_by_count":33},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31},{"id":"2404.00563","title":"Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation","created":"2024-03-31","cited_by_count":31},{"id":"2406.10485","title":"A Label is Worth a Thousand Images in Dataset Distillation","created":"2024-06-15","cited_by_count":31},{"id":"2209.14609","title":"Dataset Distillation Using Parameter Pruning","created":"2022-09-29","cited_by_count":27},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26},{"id":"2406.18561","title":"SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching","created":"2024-05-28","cited_by_count":22},{"id":"2312.00362","title":"Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement","created":"2023-12-01","cited_by_count":21},{"id":"2312.16627","title":"MIM4DD: Mutual Information Maximization for Dataset Distillation","created":"2023-12-27","cited_by_count":21},{"id":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21},{"id":"2411.19946","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","created":"2024-11-29","cited_by_count":20},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19},{"id":"2410.17193","title":"Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios","created":"2024-10-22","cited_by_count":18},{"id":"2406.03793","title":"Low-Rank Similarity Mining for Multimodal Dataset Distillation","created":"2024-06-06","cited_by_count":17},{"id":"2505.24623","title":"Hyperbolic Dataset Distillation","created":"2025-05-30","cited_by_count":15},{"id":"2408.16236","title":"Neural Spectral Decomposition for Dataset Distillation","created":"2024-08-29","cited_by_count":14},{"id":"2506.22637","title":"CaO$_2$: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation","created":"2025-06-27","cited_by_count":14},{"id":"2406.04284","title":"What is Dataset Distillation Learning?","created":"2024-06-06","cited_by_count":13},{"id":"2408.06927","title":"Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator","created":"2024-08-13","cited_by_count":13},{"id":"2502.02854","title":"TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation","created":"2025-02-05","cited_by_count":13},{"id":"1810.11189","title":"Fine-grained Video Categorization with Redundancy Reduction Attention","created":"2018-10-26","cited_by_count":12},{"id":"2506.24125","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","created":"2025-06-30","cited_by_count":11},{"id":"2405.14736","title":"GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost","created":"2024-05-23","cited_by_count":9},{"id":"2408.14506","title":"Distilling Long-tailed Datasets","created":"2024-08-24","cited_by_count":9},{"id":"2503.18267","title":"Enhancing Dataset Distillation via Non-Critical Region Refinement","created":"2025-03-24","cited_by_count":9},{"id":"2509.15472","title":"Efficient Multimodal Dataset Distillation via Generative Models","created":"2025-09-18","cited_by_count":7},{"id":"2407.14429","title":"Dataset Distillation in Medical Imaging: A Feasibility Study","created":"2024-07-19","cited_by_count":4}],"next_cursor":null}