{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"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":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"1710.05941","title":"Searching for Activation Functions","created":"2017-10-16","cited_by_count":169},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58},{"id":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","cited_by_count":40},{"id":"1908.09540","title":"Uncertainty-Aware Anticipation of Activities","created":"2019-08-26","cited_by_count":39},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36},{"id":"2207.12080","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","created":"2022-07-25","cited_by_count":35},{"id":"2405.20305","title":"Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models","created":"2024-05-30","cited_by_count":33},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23},{"id":"2207.00579","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","created":"2022-07-01","cited_by_count":18},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17},{"id":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12},{"id":"2311.15991","title":"DiffAnt: Diffusion Models for Action Anticipation","created":"2023-11-27","cited_by_count":9},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","cited_by_count":7},{"id":"2407.11954","title":"Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation","created":"2024-07-16","cited_by_count":6}],"next_cursor":null}