{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"id":"2101.12072","title":"Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting","created":"2021-01-28","cited_by_count":337},{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2302.07685","title":"Video Probabilistic Diffusion Models in Projected Latent Space","created":"2023-02-15","cited_by_count":171},{"id":"1511.05121","title":"Deep Kalman Filters","created":"2015-11-16","cited_by_count":166},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2012.00924","title":"CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction","created":"2020-12-02","cited_by_count":128},{"id":"1803.07469","title":"MAGSAC: marginalizing sample consensus","created":"2018-03-20","cited_by_count":123},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"1605.07571","title":"Sequential Neural Models with Stochastic Layers","created":"2016-05-24","cited_by_count":115},{"id":"2403.11144","title":"Is Mamba Effective for Time Series Forecasting?","created":"2024-03-17","cited_by_count":114},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2003.09572","title":"Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data","created":"2020-03-21","cited_by_count":106},{"id":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2109.05488","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","created":"2021-09-12","cited_by_count":76},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74},{"id":"2403.09898","title":"TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting","created":"2024-03-14","cited_by_count":64},{"id":"1411.7610","title":"Learning Stochastic Recurrent Networks","created":"2014-11-27","cited_by_count":60},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"2208.04464","title":"In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation","created":"2022-08-08","cited_by_count":51},{"id":"2107.10189","title":"DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation","created":"2021-07-21","cited_by_count":46},{"id":"1910.10942","title":"A Recurrent Variational Autoencoder for Speech Enhancement","created":"2019-10-24","cited_by_count":38},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37},{"id":"2310.05793","title":"DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models","created":"2023-10-09","cited_by_count":36},{"id":"2006.15560","title":"Dynamic Sampling Networks for Efficient Action Recognition in Videos","created":"2020-06-28","cited_by_count":34},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32},{"id":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24},{"id":"2203.05114","title":"OpenTAL: Towards Open Set Temporal Action Localization","created":"2022-03-10","cited_by_count":23},{"id":"2304.03959","title":"StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation","created":"2023-04-08","cited_by_count":23},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21},{"id":"2405.04370","title":"Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos","created":"2024-05-07","cited_by_count":21},{"id":"1603.04908","title":"First Person Action-Object Detection with EgoNet","created":"2016-03-15","cited_by_count":17},{"id":"2203.11305","title":"Generative Adversarial Network for Future Hand Segmentation from Egocentric Video","created":"2022-03-21","cited_by_count":16},{"id":"2406.01194","title":"AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2024-06-03","cited_by_count":14},{"id":"2404.09308","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","created":"2024-04-14","cited_by_count":12},{"id":"2312.15719","title":"Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos","created":"2023-12-25","cited_by_count":10},{"id":"2311.15991","title":"DiffAnt: Diffusion Models for Action Anticipation","created":"2023-11-27","cited_by_count":9},{"id":"2404.18648","title":"Uncertainty-boosted Robust Video Activity Anticipation","created":"2024-04-29","cited_by_count":7},{"id":"2304.11975","title":"MRSN: Multi-Relation Support Network for Video Action Detection","created":"2023-04-24","cited_by_count":5}],"next_cursor":null}