{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"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":"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":"1511.06281","title":"Density Modeling of Images using a Generalized Normalization Transformation","created":"2015-11-19","cited_by_count":127},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"2004.10290","title":"M-LVC: Multiple Frames Prediction for Learned Video Compression","created":"2020-04-21","cited_by_count":107},{"id":"2108.09993","title":"Image coding for machines: an end-to-end learned approach","created":"2021-08-23","cited_by_count":47},{"id":"2011.06409","title":"End-to-end optimized image compression for machines, a study","created":"2020-11-10","cited_by_count":30},{"id":"2004.10043","title":"Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression","created":"2020-04-21","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":"2008.00605","title":"The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study","created":"2020-08-03","cited_by_count":22},{"id":"2104.10315","title":"Visual Analysis Motivated Rate-Distortion Model for Image Coding","created":"2021-04-21","cited_by_count":21},{"id":"1704.08141","title":"Compact Descriptors for Video Analysis: the Emerging MPEG Standard","created":"2017-04-26","cited_by_count":20},{"id":"2206.05650","title":"Preprocessing Enhanced Image Compression for Machine Vision","created":"2022-06-12","cited_by_count":18},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17},{"id":"2002.07036","title":"Back-and-Forth prediction for deep tensor compression","created":"2020-02-14","cited_by_count":16},{"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":"2306.16670","title":"End-to-End Learnable Multi-Scale Feature Compression for VCM","created":"2023-06-29","cited_by_count":13},{"id":"2107.00328","title":"End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization","created":"2021-07-01","cited_by_count":12},{"id":"2112.08168","title":"Boosting Neural Image Compression for Machines Using Latent Space Masking","created":"2021-12-15","cited_by_count":11},{"id":"2002.03627","title":"End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement","created":"2020-02-10","cited_by_count":2},{"id":"2302.13581","title":"Saliency-Driven Hierarchical Learned Image Coding for Machines","created":"2023-02-27","cited_by_count":2}],"next_cursor":null}