{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2205.14987","title":"A Continuous Time Framework for Discrete Denoising Models","created":"2022-05-30","cited_by_count":451},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"2312.00858","title":"DeepCache: Accelerating Diffusion Models for Free","created":"2023-12-01","cited_by_count":359},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"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":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"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":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"2211.14304","title":"BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction","created":"2022-11-25","cited_by_count":82},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74},{"id":"2006.00626","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","created":"2020-05-31","cited_by_count":69},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"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":"2402.03478","title":"Estimating Epistemic and Aleatoric Uncertainty with a Single Model","created":"2024-02-05","cited_by_count":54},{"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":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40},{"id":"1908.09540","title":"Uncertainty-Aware Anticipation of Activities","created":"2019-08-26","cited_by_count":39},{"id":"2405.05224","title":"Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation","created":"2024-05-08","cited_by_count":37},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36},{"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":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29},{"id":"2110.02584","title":"EdiTTS: Score-based Editing for Controllable Text-to-Speech","created":"2021-10-06","cited_by_count":28},{"id":"2306.05421","title":"Stochastic Multi-Person 3D Motion Forecasting","created":"2023-06-08","cited_by_count":28},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23},{"id":"2303.14863","title":"DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion","created":"2023-03-27","cited_by_count":19},{"id":"2207.00579","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","created":"2022-07-01","cited_by_count":18},{"id":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","cited_by_count":7}],"next_cursor":null}