{"total":66,"rows":[{"id":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26,"area":null},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17,"area":null},{"id":"2403.04173","title":"Image Coding for Machines with Edge Information Learning Using Segment Anything","created":"2024-03-07","cited_by_count":17,"area":null},{"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,"area":null},{"id":"2402.02140","title":"Generative Visual Compression: A Review","created":"2024-02-03","cited_by_count":13,"area":null},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2110.09241","title":"Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics","created":"2021-10-18","cited_by_count":11,"area":null},{"id":"2312.15622","title":"Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Vision","created":"2023-12-25","cited_by_count":11,"area":null},{"id":"2407.11700","title":"Rate-Distortion-Cognition Controllable Versatile Neural Image Compression","created":"2024-07-16","cited_by_count":11,"area":null},{"id":"2209.01355","title":"Semantic Segmentation in Learned Compressed Domain","created":"2022-09-03","cited_by_count":10,"area":null},{"id":"2208.02512","title":"Scalable Video Coding for Humans and Machines","created":"2022-08-04","cited_by_count":9,"area":null},{"id":"2205.01874","title":"Joint Image Compression and Denoising via Latent-Space Scalability","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2211.06797","title":"Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling","created":"2022-11-13","cited_by_count":7,"area":null},{"id":"2209.11694","title":"Rate-Distortion in Image Coding for Machines","created":"2022-09-21","cited_by_count":6,"area":null},{"id":"2306.08941","title":"Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2404.04848","title":"Task-Aware Encoder Control for Deep Video Compression","created":"2024-04-07","cited_by_count":6,"area":null},{"id":"2405.09152","title":"Scalable Image Coding for Humans and Machines Using Feature Fusion Network","created":"2024-05-15","cited_by_count":6,"area":null},{"id":"2307.08978","title":"Learned Scalable Video Coding For Humans and Machines","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2501.04329","title":"An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2304.00689","title":"Accuracy Improvement of Object Detection in VVC Coded Video Using YOLO-v7 Features","created":"2023-04-03","cited_by_count":4,"area":null},{"id":"2307.02430","title":"Base Layer Efficiency in Scalable Human-Machine Coding","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2405.11894","title":"Refining Coded Image in Human Vision Layer Using CNN-Based Post-Processing","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2406.00791","title":"Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2112.10071","title":"A New Image Codec Paradigm for Human and Machine Uses","created":"2021-12-19","cited_by_count":3,"area":null},{"id":"2305.10453","title":"VVC+M: Plug and Play Scalable Image Coding for Humans and Machines","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2308.05959","title":"Learned Point Cloud Compression for Classification","created":"2023-08-11","cited_by_count":3,"area":null},{"id":"2401.10732","title":"Bridging the gap between image coding for machines and humans","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2405.10244","title":"Towards Task-Compatible Compressible Representations","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2506.19297","title":"Explicit Residual-Based Scalable Image Coding for Humans and Machines","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2112.14934","title":"SFU-HW-Tracks-v1: Object Tracking Dataset on Raw Video Sequences","created":"2021-12-30","cited_by_count":2,"area":null},{"id":"2210.00727","title":"Privacy-Preserving Feature Coding for Machines","created":"2022-10-03","cited_by_count":2,"area":null},{"id":"2305.02562","title":"Conditional and Residual Methods in Scalable Coding for Humans and Machines","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2305.18782","title":"VVC Extension Scheme for Object Detection Using Contrast Reduction","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2404.07698","title":"Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2411.09308","title":"DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2503.17907","title":"Guided Diffusion for the Extension of Machine Vision to Human Visual Perception","created":"2025-03-23","cited_by_count":2,"area":"diffusion"},{"id":"2506.12737","title":"Cross-architecture universal feature coding via distribution alignment","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2510.13714","title":"DeDelayed: Deleting Remote Inference Delay via On-Device Correction","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2205.01724","title":"License Plate Privacy in Collaborative Visual Analysis of Traffic Scenes","created":"2022-05-03","cited_by_count":1,"area":null},{"id":"2310.00559","title":"CPIPS: Learning to Preserve Perceptual Distances in End-to-End Image Compression","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2401.10761","title":"NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2402.12532","title":"Scalable Human-Machine Point Cloud Compression","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2404.12330","title":"A Perspective on Deep Vision Performance with Standard Image and Video Codecs","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2405.19669","title":"Texture-guided Coding for Deep Features","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2407.01017","title":"Coding for Intelligence from the Perspective of Category","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2504.02216","title":"Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2504.12997","title":"All-in-One Transferring Image Compression from Human Perception to Multi-Machine Perception","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2507.01608","title":"Perception-Oriented Latent Coding for High-Performance Compressed Domain Semantic Inference","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.15578","title":"Compress-Align-Detect: onboard change detection from unregistered images","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2511.08915","title":"Machines Serve Human: A Novel Variable Human-machine Collaborative Compression Framework","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2601.06834","title":"Enhancing Low-resolution Image Representation Through Normalizing Flows","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.21424","title":"Lossy Common Information in a Learnable Gray-Wyner Network","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2608.16696","title":"UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2310.00568","title":"Image Data Hiding in Neural Compressed Latent Representations","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2408.08211","title":"Learned Multimodal Compression for Autonomous Driving","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2509.16853","title":"ISCS: Parameter-Guided Feature Pruning for Resource-Constrained Embodied Perception","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2509.22570","title":"UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaboration","created":"2025-09-26","cited_by_count":0,"area":"mllm"},{"id":"2601.22002","title":"Understanding Rate-Distortion Performance in Distributed Transformer Inference","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.09703","title":"ProGS: Towards Progressive Coding for 3D Gaussian Splatting","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.00314","title":"Prompt-Guided Prefiltering for VLM Image Compression","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2604.05347","title":"CI-ICM: Channel Importance-driven Learned Image Coding for Machines","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.10017","title":"What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2606.21033","title":"MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts","created":"2026-06-19","cited_by_count":0,"area":"moe"},{"id":"2609.25108","title":"You've Seen Enough: Quality-Constrained Image Coding for Machines","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.37575","title":"On Task Scope and Information Retention in Source Coding","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.16552","title":"Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}