{"list":"other","total":66,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"2011.03029","title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research","created":"2020-11-05","cited_by_count":276},{"id":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"2207.05894","title":"Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression","created":"2022-07-13","cited_by_count":128},{"id":"2111.13850","title":"Temporal Context Mining for Learned Video Compression","created":"2021-11-27","cited_by_count":117},{"id":"2004.10290","title":"M-LVC: Multiple Frames Prediction for Learned Video Compression","created":"2020-04-21","cited_by_count":107},{"id":"2108.03690","title":"Enhanced Invertible Encoding for Learned Image Compression","created":"2021-08-08","cited_by_count":105},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71},{"id":"2104.14335","title":"ELF-VC: Efficient Learned Flexible-Rate Video Coding","created":"2021-04-29","cited_by_count":69},{"id":"2307.15421","title":"MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression","created":"2023-07-28","cited_by_count":58},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2206.07460","title":"Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction","created":"2022-06-15","cited_by_count":55},{"id":"2401.06197","title":"Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications","created":"2024-01-11","cited_by_count":50},{"id":"2203.02452","title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression","created":"2022-03-04","cited_by_count":45},{"id":"2203.10897","title":"Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression","created":"2022-03-21","cited_by_count":43},{"id":"2302.08899","title":"QARV: Quantization-Aware ResNet VAE for Lossy Image Compression","created":"2023-02-16","cited_by_count":32},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32},{"id":"2504.00496","title":"Learned Image Compression with Dictionary-based Entropy Model","created":"2025-04-01","cited_by_count":30},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28},{"id":"2112.08691","title":"Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning","created":"2021-12-16","cited_by_count":25},{"id":"2505.16177","title":"Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression","created":"2025-05-22","cited_by_count":25},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23},{"id":"2507.19125","title":"Learned Image Compression with Hierarchical Progressive Context Modeling","created":"2025-07-25","cited_by_count":21},{"id":"2408.08604","title":"Bi-Directional Deep Contextual Video Compression","created":"2024-08-16","cited_by_count":20},{"id":"2410.09706","title":"ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression","created":"2024-10-13","cited_by_count":20},{"id":"2503.12461","title":"MambaIC: State Space Models for High-Performance Learned Image Compression","created":"2025-03-16","cited_by_count":20},{"id":"2409.00953","title":"PNVC: Towards Practical INR-based Video Compression","created":"2024-09-02","cited_by_count":19},{"id":"2505.14541","title":"Neural Video Compression with Context Modulation","created":"2025-05-20","cited_by_count":16},{"id":"2310.01258","title":"MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device","created":"2023-10-02","cited_by_count":13},{"id":"2408.03265","title":"BVI-AOM: A New Training Dataset for Deep Video Compression Optimization","created":"2024-08-06","cited_by_count":12},{"id":"2303.05744","title":"QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression","created":"2023-03-10","cited_by_count":11},{"id":"2405.14336","title":"I$^2$VC: A Unified Framework for Intra- & Inter-frame Video Compression","created":"2024-05-23","cited_by_count":11},{"id":"2406.09754","title":"LAVIB: A Large-scale Video Interpolation Benchmark","created":"2024-06-14","cited_by_count":11},{"id":"2501.13751","title":"On Disentangled Training for Nonlinear Transform in Learned Image Compression","created":"2025-01-23","cited_by_count":9},{"id":"2411.16119","title":"Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression","created":"2024-11-25","cited_by_count":8},{"id":"2411.19320","title":"Generalized Gaussian Model for Learned Image Compression","created":"2024-11-28","cited_by_count":8},{"id":"2505.05309","title":"Augmented Deep Contexts for Spatially Embedded Video Coding","created":"2025-05-08","cited_by_count":8},{"id":"2505.09193","title":"BiECVC: Gated Diversification of Bidirectional Contexts for Learned Video Compression","created":"2025-05-14","cited_by_count":8},{"id":"2509.04118","title":"EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding","created":"2025-09-04","cited_by_count":7},{"id":"2402.18862","title":"Towards Backward-Compatible Continual Learning of Image Compression","created":"2024-02-29","cited_by_count":5},{"id":"2502.04988","title":"CMamba: Learned Image Compression with State Space Models","created":"2025-02-07","cited_by_count":5},{"id":"2502.20161","title":"Balanced Rate-Distortion Optimization in Learned Image Compression","created":"2025-02-27","cited_by_count":5},{"id":"2508.02072","title":"HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding","created":"2025-08-04","cited_by_count":5},{"id":"2510.07283","title":"Content-Adaptive Inference for State-of-the-art Learned Video Compression","created":"2025-10-08","cited_by_count":5},{"id":"2511.08938","title":"Neural B-frame Video Compression with Bi-directional Reference Harmonization","created":"2025-11-12","cited_by_count":5},{"id":"2410.00557","title":"STanH : Parametric Quantization for Variable Rate Learned Image Compression","created":"2024-10-01","cited_by_count":4},{"id":"2508.01852","title":"Context Guided Transformer Entropy Modeling for Video Compression","created":"2025-08-03","cited_by_count":3},{"id":"2510.12479","title":"MH-LVC: Multi-Hypothesis Temporal Prediction for Learned Conditional Residual Video Coding","created":"2025-10-14","cited_by_count":2},{"id":"2601.20769","title":"Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidence","created":"2026-01-28","cited_by_count":2}],"next_cursor":null}