{"list":"other","total":63,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"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":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"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":"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":"1804.06919","title":"Video Compression through Image Interpolation","created":"2018-04-18","cited_by_count":143},{"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":"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":"2304.02633","title":"HNeRV: A Hybrid Neural Representation for Videos","created":"2023-04-05","cited_by_count":100},{"id":"1908.05717","title":"Video Compression With Rate-Distortion Autoencoders","created":"2019-08-14","cited_by_count":97},{"id":"1811.06981","title":"Learned Video Compression","created":"2018-11-16","cited_by_count":89},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74},{"id":"2306.09818","title":"HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation","created":"2023-06-16","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":"2006.13560","title":"Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model","created":"2020-06-24","cited_by_count":67},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62},{"id":"2206.07460","title":"Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction","created":"2022-06-15","cited_by_count":55},{"id":"2312.02753","title":"C3: High-performance and low-complexity neural compression from a single image or video","created":"2023-12-05","cited_by_count":55},{"id":"2207.05315","title":"CANF-VC: Conditional Augmented Normalizing Flows for Video Compression","created":"2022-07-12","cited_by_count":46},{"id":"2008.09180","title":"Conditional Entropy Coding for Efficient Video Compression","created":"2020-08-20","cited_by_count":42},{"id":"2304.06544","title":"DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos","created":"2023-04-13","cited_by_count":42},{"id":"2007.04574","title":"Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model","created":"2020-07-09","cited_by_count":39},{"id":"1912.06348","title":"Learned Video Compression via Joint Spatial-Temporal Correlation Exploration","created":"2019-12-13","cited_by_count":28},{"id":"2112.09529","title":"End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression","created":"2021-12-17","cited_by_count":28},{"id":"2207.14678","title":"AlphaVC: High-Performance and Efficient Learned Video Compression","created":"2022-07-29","cited_by_count":28},{"id":"1906.09683","title":"Learning Image and Video Compression through Spatial-Temporal Energy Compaction","created":"2019-06-24","cited_by_count":27},{"id":"1804.09869","title":"Learning for Video Compression","created":"2018-04-26","cited_by_count":26},{"id":"2401.15864","title":"Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression","created":"2024-01-29","cited_by_count":23},{"id":"2307.05092","title":"Offline and Online Optical Flow Enhancement for Deep Video Compression","created":"2023-07-11","cited_by_count":17},{"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":"2112.13309","title":"Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression","created":"2021-12-26","cited_by_count":13},{"id":"2306.10681","title":"VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision","created":"2023-06-19","cited_by_count":13},{"id":"2209.09422","title":"Bit Allocation using Optimization","created":"2022-09-20","cited_by_count":9},{"id":"2312.07126","title":"Deep Hierarchical Video Compression","created":"2023-12-12","cited_by_count":9},{"id":"2303.02959","title":"Butterfly: Multiple Reference Frames Feature Propagation Mechanism for Neural Video Compression","created":"2023-03-06","cited_by_count":3}],"next_cursor":null}