{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"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":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"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":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2212.05034","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","created":"2022-12-09","cited_by_count":278},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2108.07009","title":"Pixel Difference Networks for Efficient Edge Detection","created":"2021-08-16","cited_by_count":168},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2303.05125","title":"Cones: Concept Neurons in Diffusion Models for Customized Generation","created":"2023-03-09","cited_by_count":150},{"id":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142},{"id":"2303.17599","title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models","created":"2023-03-30","cited_by_count":137},{"id":"2206.05564","title":"gDDIM: Generalized denoising diffusion implicit models","created":"2022-06-11","cited_by_count":125},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"2304.14404","title":"Motion-Conditioned Diffusion Model for Controllable Video Synthesis","created":"2023-04-27","cited_by_count":99},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"1604.07669","title":"Real-time Action Recognition with Enhanced Motion Vector CNNs","created":"2016-04-26","cited_by_count":51},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"id":"1506.01929","title":"Learning to track for spatio-temporal action localization","created":"2015-06-05","cited_by_count":44},{"id":"1901.03460","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","created":"2019-01-11","cited_by_count":36},{"id":"2304.11603","title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","created":"2023-04-23","cited_by_count":22},{"id":"1711.09618","title":"Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture","created":"2017-11-27","cited_by_count":16}],"next_cursor":null}