# Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application

arXiv: https://arxiv.org/abs/2604.09421 · HTML: https://mlsanity.com/paper/2604.09421/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [VideoSet: A Large-Scale Compressed Video Quality Dataset Based on JND Measurement](https://mlsanity.com/paper/1701.01500/) (2017)
- [TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception](https://mlsanity.com/paper/2306.05085/) (2023)
- [Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation](https://mlsanity.com/paper/2407.09853/) (2024)
- [Just Noticeable Difference for Deep Machine Vision](https://mlsanity.com/paper/2102.08168/) (2021)
- [Preprocessing Enhanced Image Compression for Machine Vision](https://mlsanity.com/paper/2206.05650/) (2022)
- [Towards Top-Down Just Noticeable Difference Estimation of Natural Images](https://mlsanity.com/paper/2108.05058/) (2021)
- [Recent Standard Development Activities on Video Coding for Machines](https://mlsanity.com/paper/2105.12653/) (2021)
- [All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation](https://mlsanity.com/paper/2409.19660/) (2024)
- [Boosting Neural Image Compression for Machines Using Latent Space Masking](https://mlsanity.com/paper/2112.08168/) (2021)
- [Rate-Distortion-Cognition Controllable Versatile Neural Image Compression](https://mlsanity.com/paper/2407.11700/) (2024)
- [A Survey on Perceptually Optimized Video Coding](https://mlsanity.com/paper/2112.12284/) (2021)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [SG-JND: Semantic-Guided Just Noticeable Distortion Predictor For Image Compression](https://mlsanity.com/paper/2408.04273/) (2024)
- [DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines](https://mlsanity.com/paper/2411.09308/) (2024)
- [Just Noticeable Visual Redundancy Forecasting: A Deep Multimodal-driven Approach](https://mlsanity.com/paper/2303.10372/) (2023)

## Abstract (arXiv)

Just Recognizable Difference (JRD) boosts coding efficiency for machine vision through visibility threshold modeling, but is currently limited to a single-task scenario. To address this issue, we propose a Multi-Task JRD (MT-JRD) dataset and an Attribute-assisted MT-JRD (AMT-JRD) model for Video Coding for Machines (VCM), enhancing both prediction accuracy and coding efficiency. First, we construct a dataset comprising 27,264 JRD annotations from machines, supporting three representative tasks including object detection, instance segmentation, and keypoint detection. Secondly, we propose the AMT-JRD prediction model, which integrates Generalized Feature Extraction Module (GFEM) and Specialized Feature Extraction Module (SFEM) to facilitate joint learning across multiple tasks. Thirdly, we innovatively incorporate object attribute information into object-wise JRD prediction through the Attribute Feature Fusion Module (AFFM), which introduces prior knowledge about object size and location. This design effectively compensates for the limitations of relying solely on image features and enhances the model's capacity to represent the perceptual mechanisms of machine vision. Finally, we apply the AMT-JRD model to VCM, where the accurately predicted JRDs are applied to reduce the coding bit rate while preserving accuracy across multiple machine vision tasks. Extensive experimental results demonstrate that AMT-JRD achieves precise and robust multi-task prediction with a mean absolute error of 3.781 and error variance of 5.332 across three tasks, outperforming the state-of-the-art single-task prediction model by 6.7% and 6.3%, respectively. Coding experiments further reveal that compared to the baseline VVC and JPEG, the AMT-JRD-based VCM improves an average of 3.861% and 7.886% Bjontegaard Delta-mean Average Precision (BD-mAP), respectively.