{"list":"other","total":72,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"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":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"id":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2010.01809","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","created":"2020-10-05","cited_by_count":271},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"id":"2003.10780","title":"Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective","created":"2020-03-24","cited_by_count":143},{"id":"2203.14197","title":"Long-Tailed Recognition via Weight Balancing","created":"2022-03-27","cited_by_count":107},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106},{"id":"2012.08548","title":"Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection","created":"2020-12-15","cited_by_count":99},{"id":"2101.10633","title":"ResLT: Residual Learning for Long-tailed Recognition","created":"2021-01-26","cited_by_count":96},{"id":"2107.09249","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","created":"2021-07-20","cited_by_count":95},{"id":"2108.02385","title":"ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot","created":"2021-08-05","cited_by_count":86},{"id":"2305.11733","title":"Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment","created":"2023-05-19","cited_by_count":75},{"id":"1907.08340","title":"Only Time Can Tell: Discovering Temporal Data for Temporal Modeling","created":"2019-07-19","cited_by_count":67},{"id":"2010.11820","title":"Posterior Re-calibration for Imbalanced Datasets","created":"2020-10-22","cited_by_count":53},{"id":"2111.09030","title":"Trustworthy Long-Tailed Classification","created":"2021-11-17","cited_by_count":51},{"id":"2104.02703","title":"Adversarial Robustness under Long-Tailed Distribution","created":"2021-04-06","cited_by_count":50},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46},{"id":"2305.08661","title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","created":"2023-05-15","cited_by_count":43},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35},{"id":"2212.02015","title":"Learning Imbalanced Data with Vision Transformers","created":"2022-12-05","cited_by_count":34},{"id":"2306.07200","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","created":"2023-06-12","cited_by_count":34},{"id":"2403.05854","title":"LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content","created":"2024-03-09","cited_by_count":33},{"id":"2103.02140","title":"PML: Progressive Margin Loss for Long-tailed Age Classification","created":"2021-03-03","cited_by_count":32},{"id":"2302.05499","title":"CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition","created":"2023-02-10","cited_by_count":30},{"id":"2008.01018","title":"RareAct: A video dataset of unusual interactions","created":"2020-08-03","cited_by_count":23},{"id":"2304.01143","title":"Use Your Head: Improving Long-Tail Video Recognition","created":"2023-04-03","cited_by_count":22},{"id":"2304.05173","title":"Improving Image Recognition by Retrieving from Web-Scale Image-Text Data","created":"2023-04-11","cited_by_count":20},{"id":"2306.06963","title":"Feature Fusion from Head to Tail for Long-Tailed Visual Recognition","created":"2023-06-12","cited_by_count":20},{"id":"2308.00994","title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","created":"2023-08-02","cited_by_count":13},{"id":"2407.06113","title":"C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition","created":"2024-07-08","cited_by_count":9},{"id":"2410.15980","title":"Learning from Neighbors: Category Extrapolation for Long-Tail Learning","created":"2024-10-21","cited_by_count":9},{"id":"2305.16573","title":"Exploring Weight Balancing on Long-Tailed Recognition Problem","created":"2023-05-26","cited_by_count":7},{"id":"2505.16341","title":"A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning","created":"2025-05-22","cited_by_count":7},{"id":"2409.18733","title":"Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval","created":"2024-09-26","cited_by_count":5},{"id":"2512.02016","title":"Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now","created":"2025-12-01","cited_by_count":5},{"id":"2211.13471","title":"Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition","created":"2022-11-24","cited_by_count":3},{"id":"2212.01638","title":"VLG: General Video Recognition with Web Textual Knowledge","created":"2022-12-03","cited_by_count":3},{"id":"2205.10788","title":"Learning Muti-expert Distribution Calibration for Long-tailed Video Classification","created":"2022-05-22","cited_by_count":2},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2}],"next_cursor":null}