{"total":80,"rows":[{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2205.13129","title":"Wireless Deep Video Semantic Transmission","created":"2022-05-26","cited_by_count":50,"area":null},{"id":"2409.08481","title":"USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s","created":"2024-09-13","cited_by_count":37,"area":null},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31,"area":null},{"id":"2112.10948","title":"Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems","created":"2021-12-21","cited_by_count":30,"area":null},{"id":"2112.09300","title":"Towards End-to-End Image Compression and Analysis with Transformers","created":"2021-12-17","cited_by_count":26,"area":null},{"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":"2102.06841","title":"Collaborative Intelligence: Challenges and Opportunities","created":"2021-02-13","cited_by_count":19,"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":"2105.12653","title":"Recent Standard Development Activities on Video Coding for Machines","created":"2021-05-26","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":"2107.00328","title":"End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization","created":"2021-07-01","cited_by_count":12,"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":"2103.04178","title":"End-to-end optimized image compression for multiple machine tasks","created":"2021-03-06","cited_by_count":9,"area":null},{"id":"2208.02512","title":"Scalable Video Coding for Humans and Machines","created":"2022-08-04","cited_by_count":9,"area":null},{"id":"2201.12477","title":"An Indirect Rate-Distortion Characterization for Semantic Sources: General Model and the Case of Gaussian Observation","created":"2022-01-29","cited_by_count":8,"area":null},{"id":"2203.05890","title":"Video Coding for Machines with Feature-Based Rate-Distortion Optimization","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2211.04339","title":"Toward Adaptive Semantic Communications: Efficient Data Transmission via Online Learned Nonlinear Transform Source-Channel Coding","created":"2022-11-08","cited_by_count":8,"area":null},{"id":"2201.10162","title":"Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks","created":"2022-01-25","cited_by_count":7,"area":null},{"id":"2204.07314","title":"Feature Compression for Rate Constrained Object Detection on the Edge","created":"2022-04-15","cited_by_count":7,"area":null},{"id":"2204.12534","title":"AccMPEG: Optimizing Video Encoding for Video Analytics","created":"2022-04-26","cited_by_count":7,"area":null},{"id":"2305.02578","title":"Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2308.13984","title":"Image Coding for Machines with Object Region Learning","created":"2023-08-27","cited_by_count":7,"area":null},{"id":"2304.06896","title":"Machine Perception-Driven Image Compression: A Layered Generative Approach","created":"2023-04-14","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":"2410.06149","title":"Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach","created":"2024-10-08","cited_by_count":6,"area":"diffusion"},{"id":"2106.05531","title":"CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence","created":"2021-06-10","cited_by_count":5,"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":"2408.08575","title":"Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs","created":"2024-08-16","cited_by_count":5,"area":"mllm"},{"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":"2112.10071","title":"A New Image Codec Paradigm for Human and Machine Uses","created":"2021-12-19","cited_by_count":3,"area":null},{"id":"2208.07313","title":"Task Oriented Video Coding: A Survey","created":"2022-08-15","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":"2405.03500","title":"A Rate-Distortion-Classification Approach for Lossy Image Compression","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2503.19278","title":"Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2506.07412","title":"Compressed Feature Quality Assessment: Dataset and Baselines","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2601.21933","title":"Just Noticeable Difference Modeling for Deep Visual Features","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2603.17546","title":"ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2102.01307","title":"Human-Machine Collaborative Video Coding Through Cuboidal Partitioning","created":"2021-02-02","cited_by_count":2,"area":null},{"id":"2308.16215","title":"Deep Video Codec Control for Vision Models","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2402.18402","title":"A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2406.12367","title":"Competitive Learning for Achieving Content-specific Filters in Video Coding for Machines","created":"2024-06-18","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":"2602.12866","title":"Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2106.08512","title":"Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2201.02689","title":"Video Coding for Machines: Partial transmission of SIFT features","created":"2022-01-07","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":"2403.10202","title":"Learning on JPEG-LDPC Compressed Images: Classifying with Syndromes","created":"2024-03-15","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":"2407.02713","title":"Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation","created":"2024-07-02","cited_by_count":1,"area":"distill"},{"id":"2407.11590","title":"Rethinking Learned Image Compression: Context is All You Need","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2602.00483","title":"Recent Advances of End-to-End Video Coding Technologies for AVS Standard Development","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2605.24025","title":"Towards Large Model Feature Coding","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.03279","title":"A Geometric Lens on Physics-Aligned Data Compression","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.16253","title":"Learned Image Compression for Vision-Language-Action Models","created":"2026-06-15","cited_by_count":1,"area":"vla"},{"id":"2608.16696","title":"UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2609.01200","title":"Compressing AI Traffic: Standardized Neural Network Coding of Visual-Token Representations in Split Vision-Language Inference","created":"2026-09-01","cited_by_count":1,"area":"mllm"},{"id":"2102.00142","title":"Latent-Space Inpainting for Packet Loss Concealment in Collaborative Object Detection","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2102.04018","title":"Analysis of Latent-Space Motion for Collaborative Intelligence","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2111.06263","title":"Towards Live Video Analytics with On-Drone Deeper-yet-Compatible Compression","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2211.13137","title":"Pruned Lightweight Encoders for Computer Vision","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2503.11954","title":"Goal-Oriented Source Coding using LDPC Codes for Compressed-Domain Image Classification","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2504.12923","title":"Efficient Masked Image Compression with Position-Indexed Self-Attention","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2506.11545","title":"FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution","created":"2025-06-13","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":"2509.24805","title":"RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off","created":"2025-09-29","cited_by_count":0,"area":null},{"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":"2604.05375","title":"DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2604.09421","title":"Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.09479","title":"ML-CLIPSim: Multi-Layer CLIP Similarity for Machine-Oriented Image Quality","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.19515","title":"BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.08832","title":"Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding","created":"2026-08-09","cited_by_count":0,"area":null},{"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}],"next_cursor":null}