{"list":"other","total":86,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"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":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"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":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2403.12015","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","created":"2024-03-18","cited_by_count":279},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"1804.02958","title":"Generative Adversarial Networks for Extreme Learned Image Compression","created":"2018-04-09","cited_by_count":219},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2103.15306","title":"Checkerboard Context Model for Efficient Learned Image Compression","created":"2021-03-29","cited_by_count":202},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"2310.13268","title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","created":"2023-10-20","cited_by_count":161},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"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":"2303.09769","title":"Denoising Diffusion Autoencoders are Unified Self-supervised Learners","created":"2023-03-17","cited_by_count":130},{"id":"2202.05492","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","created":"2022-02-11","cited_by_count":107},{"id":"2108.03690","title":"Enhanced Invertible Encoding for Learned Image Compression","created":"2021-08-08","cited_by_count":105},{"id":"2310.10325","title":"Towards image compression with perfect realism at ultra-low bitrates","created":"2023-10-16","cited_by_count":103},{"id":"1910.14315","title":"BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems","created":"2019-10-31","cited_by_count":95},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94},{"id":"2401.14404","title":"Deconstructing Denoising Diffusion Models for Self-Supervised Learning","created":"2024-01-25","cited_by_count":91},{"id":"2206.08889","title":"Lossy Compression with Gaussian Diffusion","created":"2022-06-17","cited_by_count":90},{"id":"2011.09704","title":"Causal Contextual Prediction for Learned Image Compression","created":"2020-11-19","cited_by_count":73},{"id":"1902.01000","title":"BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services","created":"2019-02-04","cited_by_count":68},{"id":"2404.18820","title":"Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior","created":"2024-04-29","cited_by_count":60},{"id":"2307.08702","title":"Diffusion Models Beat GANs on Image Classification","created":"2023-07-17","cited_by_count":58},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2112.04487","title":"Joint Global and Local Hierarchical Priors for Learned Image Compression","created":"2021-12-08","cited_by_count":54},{"id":"2305.18231","title":"High-Fidelity Image Compression with Score-based Generative Models","created":"2023-05-26","cited_by_count":54},{"id":"1802.03931","title":"Deep feature compression for collaborative object detection","created":"2018-02-12","cited_by_count":48},{"id":"2106.10311","title":"Universal Rate-Distortion-Perception Representations for Lossy Compression","created":"2021-06-18","cited_by_count":47},{"id":"2108.09993","title":"Image coding for machines: an end-to-end learned approach","created":"2021-08-23","cited_by_count":47},{"id":"2007.11797","title":"End-to-end Learning of Compressible Features","created":"2020-07-23","cited_by_count":43},{"id":"2404.08580","title":"Lossy Image Compression with Foundation Diffusion Models","created":"2024-04-12","cited_by_count":36},{"id":"2301.05489","title":"A Residual Diffusion Model for High Perceptual Quality Codec Augmentation","created":"2023-01-13","cited_by_count":35},{"id":"2306.05085","title":"TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception","created":"2023-06-08","cited_by_count":32},{"id":"2211.07793","title":"Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models","created":"2022-11-14","cited_by_count":31},{"id":"2011.06409","title":"End-to-end optimized image compression for machines, a study","created":"2020-11-10","cited_by_count":30},{"id":"2008.10314","title":"Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks","created":"2020-08-24","cited_by_count":29},{"id":"2401.08920","title":"Idempotence and Perceptual Image Compression","created":"2024-01-17","cited_by_count":29},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28},{"id":"2106.02782","title":"On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework","created":"2021-06-05","cited_by_count":27},{"id":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26},{"id":"2106.03511","title":"Task-driven Semantic Coding via Reinforcement Learning","created":"2021-06-07","cited_by_count":25},{"id":"1803.05788","title":"DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework","created":"2018-03-14","cited_by_count":23},{"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":"2503.12461","title":"MambaIC: State Space Models for High-Performance Learned Image Compression","created":"2025-03-16","cited_by_count":20},{"id":"2206.05650","title":"Preprocessing Enhanced Image Compression for Machine Vision","created":"2022-06-12","cited_by_count":18},{"id":"2409.20255","title":"PerCo (SD): Open Perceptual Compression","created":"2024-09-30","cited_by_count":18},{"id":"2009.12430","title":"Pareto-Optimal Bit Allocation for Collaborative Intelligence","created":"2020-09-25","cited_by_count":17},{"id":"2405.16817","title":"Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model","created":"2024-05-27","cited_by_count":17},{"id":"2001.06580","title":"A GAN-based Tunable Image Compression System","created":"2020-01-18","cited_by_count":14},{"id":"2002.07048","title":"Bit Allocation for Multi-Task Collaborative Intelligence","created":"2020-02-14","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":"2404.04916","title":"Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder","created":"2024-04-07","cited_by_count":13},{"id":"2112.08168","title":"Boosting Neural Image Compression for Machines Using Latent Space Masking","created":"2021-12-15","cited_by_count":11},{"id":"1801.09468","title":"DeepSIC: Deep Semantic Image Compression","created":"2018-01-29","cited_by_count":10},{"id":"2003.02874","title":"Optimizing JPEG Quantization for Classification Networks","created":"2020-03-05","cited_by_count":6},{"id":"2410.06149","title":"Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach","created":"2024-10-08","cited_by_count":6},{"id":"2407.11224","title":"Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding","created":"2024-07-15","cited_by_count":4},{"id":"2208.11529","title":"Hierarchical Reinforcement Learning Based Video Semantic Coding for Segmentation","created":"2022-08-24","cited_by_count":3},{"id":"2406.12367","title":"Competitive Learning for Achieving Content-specific Filters in Video Coding for Machines","created":"2024-06-18","cited_by_count":2},{"id":"2405.19669","title":"Texture-guided Coding for Deep Features","created":"2024-05-30","cited_by_count":1}],"next_cursor":null}