{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1809.05679","title":"Graph Convolutional Networks for Text Classification","created":"2018-09-15","cited_by_count":345},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2004.04581","title":"Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation","created":"2020-04-09","cited_by_count":300},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","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":"2004.00121","title":"StyleRig: Rigging StyleGAN for 3D Control over Portrait Images","created":"2020-03-31","cited_by_count":268},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2004.07703","title":"Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision","created":"2020-04-16","cited_by_count":198},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"1903.07256","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","created":"2019-03-18","cited_by_count":171},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1909.12224","title":"Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis","created":"2019-09-26","cited_by_count":161},{"id":"1902.09130","title":"An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition","created":"2019-02-25","cited_by_count":151},{"id":"2003.13045","title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","created":"2020-03-29","cited_by_count":120},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"1903.06874","title":"Fast Interactive Object Annotation with Curve-GCN","created":"2019-03-16","cited_by_count":95},{"id":"2008.08171","title":"Learning to Generate Diverse Dance Motions with Transformer","created":"2020-08-18","cited_by_count":85},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"1906.07510","title":"Attention Guided Graph Convolutional Networks for Relation Extraction","created":"2019-06-18","cited_by_count":82},{"id":"2006.06119","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","created":"2020-06-11","cited_by_count":81},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51},{"id":"1904.02749","title":"Learning to Cluster Faces on an Affinity Graph","created":"2019-04-04","cited_by_count":50},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2008.04381","title":"Bipartite Graph Reasoning GANs for Person Image Generation","created":"2020-08-10","cited_by_count":34},{"id":"2011.12999","title":"Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio","created":"2020-11-25","cited_by_count":33},{"id":"2009.07637","title":"ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit","created":"2020-09-16","cited_by_count":31},{"id":"1904.00129","title":"Dance Dance Generation: Motion Transfer for Internet Videos","created":"2019-03-30","cited_by_count":28},{"id":"2005.00669","title":"Contrastive Self-Supervised Learning for Commonsense Reasoning","created":"2020-05-02","cited_by_count":25},{"id":"2009.08015","title":"Temporally Guided Music-to-Body-Movement Generation","created":"2020-09-17","cited_by_count":21},{"id":"2206.06420","title":"GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation","created":"2022-06-13","cited_by_count":21},{"id":"2003.14142","title":"Look-into-Object: Self-supervised Structure Modeling for Object Recognition","created":"2020-03-31","cited_by_count":20},{"id":"2004.02331","title":"Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics","created":"2020-04-05","cited_by_count":19},{"id":"2303.08225","title":"Graph Transformer GANs for Graph-Constrained House Generation","created":"2023-03-14","cited_by_count":19},{"id":"2004.05830","title":"From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech","created":"2020-04-13","cited_by_count":17},{"id":"2005.03358","title":"Self-Supervised Human Depth Estimation from Monocular Videos","created":"2020-05-07","cited_by_count":17},{"id":"1911.04069","title":"Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music","created":"2019-11-11","cited_by_count":14},{"id":"2301.10134","title":"Bipartite Graph Diffusion Model for Human Interaction Generation","created":"2023-01-24","cited_by_count":11},{"id":"2112.07423","title":"Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking","created":"2021-12-14","cited_by_count":9},{"id":"2211.06719","title":"Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis","created":"2022-11-12","cited_by_count":9},{"id":"2005.09816","title":"Relevant Region Prediction for Crowd Counting","created":"2020-05-20","cited_by_count":6},{"id":"2401.07721","title":"Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation","created":"2024-01-15","cited_by_count":5}],"next_cursor":null}