{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"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":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"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":"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":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"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":"1809.10452","title":"Context-adaptive Entropy Model for End-to-end Optimized Image Compression","created":"2018-09-27","cited_by_count":143},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116},{"id":"2503.03125","title":"Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving","created":"2025-03-05","cited_by_count":84},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62},{"id":"2203.14675","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","created":"2022-03-28","cited_by_count":59},{"id":"2112.04487","title":"Joint Global and Local Hierarchical Priors for Learned Image Compression","created":"2021-12-08","cited_by_count":54},{"id":"2108.09993","title":"Image coding for machines: an end-to-end learned approach","created":"2021-08-23","cited_by_count":47},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42},{"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":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31},{"id":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26},{"id":"2505.16091","title":"OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates","created":"2025-05-22","cited_by_count":26},{"id":"2112.06334","title":"DPICT: Deep Progressive Image Compression Using Trit-Planes","created":"2021-12-12","cited_by_count":25},{"id":"2102.02913","title":"Progressive Neural Image Compression with Nested Quantization and Latent Ordering","created":"2021-02-04","cited_by_count":24},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22},{"id":"2303.05715","title":"Context-Based Trit-Plane Coding for Progressive Image Compression","created":"2023-03-10","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":"2403.04173","title":"Image Coding for Machines with Edge Information Learning Using Segment Anything","created":"2024-03-07","cited_by_count":17},{"id":"2406.00758","title":"Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation","created":"2024-06-02","cited_by_count":16},{"id":"2409.19660","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","created":"2024-09-29","cited_by_count":14},{"id":"2305.02145","title":"ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training","created":"2023-05-03","cited_by_count":13},{"id":"2407.11700","title":"Rate-Distortion-Cognition Controllable Versatile Neural Image Compression","created":"2024-07-16","cited_by_count":11},{"id":"2305.07783","title":"ROI-based Deep Image Compression with Swin Transformers","created":"2023-05-12","cited_by_count":10},{"id":"2412.10935","title":"Progressive Compression with Universally Quantized Diffusion Models","created":"2024-12-14","cited_by_count":10},{"id":"2408.12150","title":"DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Coding","created":"2024-08-22","cited_by_count":5},{"id":"2304.08288","title":"Toward Auto-evaluation with Confidence-based Category Relation-aware Regression","created":"2023-04-17","cited_by_count":4},{"id":"2411.10185","title":"Efficient Progressive Image Compression with Variance-aware Masking","created":"2024-11-15","cited_by_count":4},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4},{"id":"2506.19297","title":"Explicit Residual-Based Scalable Image Coding for Humans and Machines","created":"2025-06-24","cited_by_count":3},{"id":"2512.18200","title":"SLIM: Semantic-based Low-bitrate Image compression for Machines by leveraging diffusion","created":"2025-12-20","cited_by_count":3},{"id":"2203.13467","title":"RD-Optimized Trit-Plane Coding of Deep Compressed Image Latent Tensors","created":"2022-03-25","cited_by_count":2},{"id":"2503.17907","title":"Guided Diffusion for the Extension of Machine Vision to Human Visual Perception","created":"2025-03-23","cited_by_count":2}],"next_cursor":null}