{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"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":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"1703.00395","title":"Lossy Image Compression with Compressive Autoencoders","created":"2017-03-01","cited_by_count":294},{"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":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"1812.02898","title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution","created":"2018-12-07","cited_by_count":226},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"1511.06085","title":"Variable Rate Image Compression with Recurrent Neural Networks","created":"2015-11-19","cited_by_count":173},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"2203.08450","title":"The Devil Is in the Details: Window-based Attention for Image Compression","created":"2022-03-16","cited_by_count":147},{"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":"2402.17414","title":"Neural Video Compression with Feature Modulation","created":"2024-02-27","cited_by_count":123},{"id":"2111.13850","title":"Temporal Context Mining for Learned Video Compression","created":"2021-11-27","cited_by_count":117},{"id":"1909.04802","title":"Variable Rate Deep Image Compression With a Conditional Autoencoder","created":"2019-09-11","cited_by_count":114},{"id":"2004.10290","title":"M-LVC: Multiple Frames Prediction for Learned Video Compression","created":"2020-04-21","cited_by_count":107},{"id":"2202.05492","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","created":"2022-02-11","cited_by_count":107},{"id":"2003.01966","title":"Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement","created":"2020-03-04","cited_by_count":90},{"id":"1811.06981","title":"Learned Video Compression","created":"2018-11-16","cited_by_count":89},{"id":"2003.02012","title":"Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation","created":"2020-03-04","cited_by_count":85},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74},{"id":"2003.11282","title":"Content Adaptive and Error Propagation Aware Deep Video Compression","created":"2020-03-25","cited_by_count":72},{"id":"2104.14335","title":"ELF-VC: Efficient Learned Flexible-Rate Video Coding","created":"2021-04-29","cited_by_count":69},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2008.09180","title":"Conditional Entropy Coding for Efficient Video Compression","created":"2020-08-20","cited_by_count":42},{"id":"1912.05526","title":"Variable Rate Deep Image Compression with Modulated Autoencoder","created":"2019-12-11","cited_by_count":40},{"id":"2007.04574","title":"Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model","created":"2020-07-09","cited_by_count":39},{"id":"2012.09550","title":"Learned Block-based Hybrid Image Compression","created":"2020-12-17","cited_by_count":30},{"id":"2207.14678","title":"AlphaVC: High-Performance and Efficient Learned Video Compression","created":"2022-07-29","cited_by_count":28},{"id":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26},{"id":"2209.01769","title":"B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows","created":"2022-09-05","cited_by_count":18},{"id":"2211.04104","title":"Selective compression learning of latent representations for variable-rate image compression","created":"2022-11-08","cited_by_count":17},{"id":"2004.08283","title":"Learned Video Compression with Feature-level Residuals","created":"2020-04-17","cited_by_count":15},{"id":"2211.07004","title":"Advancing Learned Video Compression with In-loop Frame Prediction","created":"2022-11-13","cited_by_count":14},{"id":"2108.04103","title":"End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation","created":"2021-08-05","cited_by_count":13},{"id":"2501.13751","title":"On Disentangled Training for Nonlinear Transform in Learned Image Compression","created":"2025-01-23","cited_by_count":9},{"id":"2104.06083","title":"Spatiotemporal Entropy Model is All You Need for Learned Video Compression","created":"2021-04-13","cited_by_count":4},{"id":"2410.02598","title":"High-Efficiency Neural Video Compression via Hierarchical Predictive Learning","created":"2024-10-03","cited_by_count":2}],"next_cursor":null}