{"total":501,"rows":[{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155,"area":null},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2104.10353","title":"Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning","created":"2021-04-21","cited_by_count":106,"area":null},{"id":"2306.11867","title":"Personalized Federated Learning with Feature Alignment and Classifier Collaboration","created":"2023-06-20","cited_by_count":97,"area":null},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94,"area":null},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84,"area":null},{"id":"2106.00445","title":"Sample Selection with Uncertainty of Losses for Learning with Noisy Labels","created":"2021-06-01","cited_by_count":79,"area":null},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75,"area":null},{"id":"2311.04056","title":"Multi-View Causal Representation Learning with Partial Observability","created":"2023-11-07","cited_by_count":74,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2212.08062","title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation","created":"2022-12-15","cited_by_count":69,"area":null},{"id":"2312.02902","title":"HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting","created":"2023-12-05","cited_by_count":60,"area":null},{"id":"2108.00981","title":"PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series","created":"2021-08-02","cited_by_count":58,"area":null},{"id":"2110.09994","title":"DPFM: Deep Partial Functional Maps","created":"2021-10-19","cited_by_count":58,"area":null},{"id":"2107.11472","title":"Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2104.02243","title":"3D-to-2D Distillation for Indoor Scene Parsing","created":"2021-04-06","cited_by_count":48,"area":null},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2204.08446","title":"VSA: Learning Varied-Size Window Attention in Vision Transformers","created":"2022-04-18","cited_by_count":43,"area":null},{"id":"2206.12227","title":"Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective","created":"2022-06-24","cited_by_count":42,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2104.07012","title":"Sparse Attention with Linear Units","created":"2021-04-14","cited_by_count":41,"area":null},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39,"area":null},{"id":"2302.06594","title":"Geometric Clifford Algebra Networks","created":"2023-02-13","cited_by_count":38,"area":null},{"id":"2105.02685","title":"A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations","created":"2021-05-06","cited_by_count":37,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2106.02022","title":"Single Image Depth Prediction with Wavelet Decomposition","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2109.00666","title":"TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks","created":"2021-09-02","cited_by_count":34,"area":null},{"id":"2303.11162","title":"Picture that Sketch: Photorealistic Image Generation from Abstract Sketches","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2112.09312","title":"MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling","created":"2021-12-17","cited_by_count":32,"area":null},{"id":"2205.11775","title":"Constrained Monotonic Neural Networks","created":"2022-05-24","cited_by_count":32,"area":null},{"id":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2104.12961","title":"Unsupervised Multi-Source Domain Adaptation for Person Re-Identification","created":"2021-04-27","cited_by_count":30,"area":null},{"id":"2207.13066","title":"NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers","created":"2022-07-26","cited_by_count":30,"area":null},{"id":"2103.01537","title":"Few-shot Open-set Recognition by Transformation Consistency","created":"2021-03-02","cited_by_count":29,"area":null},{"id":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2210.06823","title":"Scalable Neural Video Representations with Learnable Positional Features","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2310.05316","title":"Understanding the Feature Norm for Out-of-Distribution Detection","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2103.04181","title":"Contextual Dropout: An Efficient Sample-Dependent Dropout Module","created":"2021-03-06","cited_by_count":26,"area":null},{"id":"2108.06337","title":"Dual Path Learning for Domain Adaptation of Semantic Segmentation","created":"2021-08-13","cited_by_count":26,"area":null},{"id":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26,"area":null},{"id":"2312.00246","title":"Directions of Curvature as an Explanation for Loss of Plasticity","created":"2023-11-30","cited_by_count":26,"area":null},{"id":"2103.10592","title":"Fusion-FlowNet: Energy-Efficient Optical Flow Estimation using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures","created":"2021-03-19","cited_by_count":25,"area":null},{"id":"2107.07740","title":"MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition","created":"2021-07-16","cited_by_count":25,"area":null},{"id":"2211.10754","title":"HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities","created":"2022-11-19","cited_by_count":25,"area":null},{"id":"2212.13881","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","created":"2022-12-28","cited_by_count":25,"area":null},{"id":"2305.17476","title":"Toward Understanding Generative Data Augmentation","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2203.16462","title":"Convergence of gradient descent for deep neural networks","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2412.01801","title":"SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2110.00306","title":"Leveraging power grid topology in machine learning assisted optimal power flow","created":"2021-10-01","cited_by_count":22,"area":null},{"id":"2301.09479","title":"Modality-Agnostic Variational Compression of Implicit Neural Representations","created":"2023-01-23","cited_by_count":22,"area":null},{"id":"2101.02374","title":"Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition","created":"2021-01-07","cited_by_count":21,"area":null},{"id":"2103.13225","title":"Structure-Aware Face Clustering on a Large-Scale Graph with $\\bf{10^{7}}$ Nodes","created":"2021-03-24","cited_by_count":21,"area":null},{"id":"2206.07551","title":"Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2209.01578","title":"Spatial-Temporal Transformer for Video Snapshot Compressive Imaging","created":"2022-09-04","cited_by_count":21,"area":null},{"id":"2112.05195","title":"Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs","created":"2021-12-09","cited_by_count":20,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"area":null},{"id":"2107.11639","title":"Self-Conditioned Probabilistic Learning of Video Rescaling","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2202.04350","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","created":"2022-02-09","cited_by_count":19,"area":null},{"id":"2107.13994","title":"Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation","created":"2021-07-29","cited_by_count":18,"area":null},{"id":"2112.03517","title":"CG-NeRF: Conditional Generative Neural Radiance Fields","created":"2021-12-07","cited_by_count":18,"area":null},{"id":"2205.00578","title":"Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials","created":"2022-05-01","cited_by_count":18,"area":null},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2212.07778","title":"Efficient Visual Computing with Camera RAW Snapshots","created":"2022-12-15","cited_by_count":18,"area":null},{"id":"2101.10011","title":"They See Me Rollin': Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensors","created":"2021-01-25","cited_by_count":17,"area":null},{"id":"2104.03838","title":"Speech Denoising Without Clean Training Data: A Noise2Noise Approach","created":"2021-04-08","cited_by_count":17,"area":null},{"id":"2108.00131","title":"Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks","created":"2021-07-31","cited_by_count":17,"area":null},{"id":"2109.07557","title":"CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations","created":"2021-09-15","cited_by_count":17,"area":null},{"id":"2507.19359","title":"SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning","created":"2025-07-25","cited_by_count":17,"area":null},{"id":"2303.16198","title":"Multi-modal learning for geospatial vegetation forecasting","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2308.06749","title":"FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table","created":"2023-08-13","cited_by_count":16,"area":null},{"id":"2105.03085","title":"Toward Interactive Modulation for Photo-Realistic Image Restoration","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2106.04751","title":"Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Prediction","created":"2021-06-09","cited_by_count":15,"area":null},{"id":"2109.00922","title":"Improving Multimodal fusion via Mutual Dependency Maximisation","created":"2021-08-31","cited_by_count":15,"area":null},{"id":"2107.12342","title":"Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning","created":"2021-07-26","cited_by_count":14,"area":null},{"id":"2203.10480","title":"Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey","created":"2022-03-20","cited_by_count":14,"area":null},{"id":"2205.03589","title":"Learning Disentangled Textual Representations via Statistical Measures of Similarity","created":"2022-05-07","cited_by_count":14,"area":null},{"id":"2410.20634","title":"Plastic Learning with Deep Fourier Features","created":"2024-10-27","cited_by_count":14,"area":null},{"id":"2101.09957","title":"Activation Functions in Artificial Neural Networks: A Systematic Overview","created":"2021-01-25","cited_by_count":13,"area":null},{"id":"2106.08408","title":"Seeing Through Clouds in Satellite Images","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2306.16670","title":"End-to-End Learnable Multi-Scale Feature Compression for VCM","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2101.08204","title":"secureTF: A Secure TensorFlow Framework","created":"2021-01-20","cited_by_count":12,"area":null},{"id":"2102.10590","title":"Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM","created":"2021-02-21","cited_by_count":12,"area":null},{"id":"2105.04046","title":"A likelihood approach to nonparametric estimation of a singular distribution using deep generative models","created":"2021-05-09","cited_by_count":12,"area":null},{"id":"2201.04125","title":"Spectrum Surveying: Active Radio Map Estimation with Autonomous UAVs","created":"2022-01-11","cited_by_count":12,"area":null},{"id":"2202.06281","title":"Graph-adaptive Rectified Linear Unit for Graph Neural Networks","created":"2022-02-13","cited_by_count":12,"area":null},{"id":"2205.13120","title":"Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission","created":"2022-05-26","cited_by_count":12,"area":null},{"id":"2210.05766","title":"Match Cutting: Finding Cuts with Smooth Visual Transitions","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2312.03587","title":"Language-Informed Visual Concept Learning","created":"2023-12-06","cited_by_count":12,"area":null},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2103.04683","title":"Learning Graph Neural Networks with Positive and Unlabeled Nodes","created":"2021-03-08","cited_by_count":11,"area":null},{"id":"2106.08541","title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","created":"2021-06-16","cited_by_count":11,"area":null},{"id":"2203.03099","title":"Singular Value Perturbation and Deep Network Optimization","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2207.12165","title":"dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification","created":"2022-07-25","cited_by_count":11,"area":null},{"id":"2208.13811","title":"Synthetic Latent Fingerprint Generator","created":"2022-08-29","cited_by_count":11,"area":null},{"id":"2304.01518","title":"Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation","created":"2023-04-04","cited_by_count":11,"area":null},{"id":"2306.01596","title":"Two-View Geometry Scoring Without Correspondences","created":"2023-06-02","cited_by_count":11,"area":null}],"next_cursor":"100"}