{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"2212.00792","title":"SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction","created":"2022-12-01","cited_by_count":216},{"id":"2203.09516","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","created":"2022-03-17","cited_by_count":208},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"2211.09869","title":"RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation","created":"2022-11-17","cited_by_count":162},{"id":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"2209.08725","title":"Neural Wavelet-domain Diffusion for 3D Shape Generation","created":"2022-09-19","cited_by_count":132},{"id":"2305.04461","title":"Locally Attentional SDF Diffusion for Controllable 3D Shape Generation","created":"2023-05-08","cited_by_count":130},{"id":"2212.03293","title":"Diffusion-SDF: Text-to-Shape via Voxelized Diffusion","created":"2022-12-06","cited_by_count":128},{"id":"2005.02819","title":"Geoopt: Riemannian Optimization in PyTorch","created":"2020-05-06","cited_by_count":114},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111},{"id":"2303.16509","title":"HoloDiffusion: Training a 3D Diffusion Model using 2D Images","created":"2023-03-29","cited_by_count":106},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102},{"id":"2305.06611","title":"Hyperbolic Deep Learning in Computer Vision: A Survey","created":"2023-05-11","cited_by_count":73},{"id":"2203.14622","title":"Towards Implicit Text-Guided 3D Shape Generation","created":"2022-03-28","cited_by_count":68},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62},{"id":"2304.03869","title":"Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis","created":"2023-04-07","cited_by_count":51},{"id":"2211.01427","title":"CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language","created":"2022-11-02","cited_by_count":46},{"id":"2202.13852","title":"Hyperbolic Graph Neural Networks: A Review of Methods and Applications","created":"2022-02-28","cited_by_count":40},{"id":"1606.05491","title":"Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings","created":"2016-06-17","cited_by_count":27},{"id":"2211.12347","title":"The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation","created":"2022-11-22","cited_by_count":22},{"id":"2310.18511","title":"3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition","created":"2023-10-27","cited_by_count":21},{"id":"1906.02181","title":"Syntax-Infused Variational Autoencoder for Text Generation","created":"2019-06-05","cited_by_count":19},{"id":"2209.10318","title":"Rethinking the compositionality of point clouds through regularization in the hyperbolic space","created":"2022-09-21","cited_by_count":18},{"id":"2111.14673","title":"3D Compositional Zero-shot Learning with DeCompositional Consensus","created":"2021-11-29","cited_by_count":16},{"id":"2304.01900","title":"PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion","created":"2023-04-04","cited_by_count":12},{"id":"2309.02965","title":"Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction","created":"2023-09-06","cited_by_count":10}],"next_cursor":null}