# Convolutions Need Registers Too: HVS-Inspired Dynamic Attention for Video Quality Assessment

arXiv: https://arxiv.org/abs/2601.11045 · HTML: https://mlsanity.com/paper/2601.11045/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content](https://mlsanity.com/paper/2005.14354/) (2020)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Large-Scale Study of Perceptual Video Quality](https://mlsanity.com/paper/1803.01761/) (2018)
- [Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception](https://mlsanity.com/paper/2108.08505/) (2021)
- [Unified Image and Video Saliency Modeling](https://mlsanity.com/paper/2003.05477/) (2020)
- [Revisiting Video Saliency: A Large-scale Benchmark and a New Model](https://mlsanity.com/paper/1801.07424/) (2018)
- [TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection](https://mlsanity.com/paper/1908.05786/) (2019)
- [Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models](https://mlsanity.com/paper/2307.13981/) (2023)
- [PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild](https://mlsanity.com/paper/2405.17765/) (2024)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction](https://mlsanity.com/paper/2403.01226/) (2024)
- [KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception](https://mlsanity.com/paper/2503.10259/) (2025)
- [ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment](https://mlsanity.com/paper/2407.11496/) (2024)
- [Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling](https://mlsanity.com/paper/2501.07087/) (2025)
- [Where to look at the movies : Analyzing visual attention to understand movie editing](https://mlsanity.com/paper/2102.13378/) (2021)

## Built on by (most cited first, 1 of 1)

- [Multimodal Confidence Modeling in Audio-Visual Quality Assessment](https://mlsanity.com/paper/2605.01219/) (2026)

## Abstract (arXiv)

No-reference video quality assessment (NR-VQA) estimates perceptual quality without a reference video, which is often challenging. While recent techniques leverage saliency or transformer attention, they merely address global context of the video signal by using static maps as auxiliary inputs rather than embedding context fundamentally within feature extraction of the video sequence. We present Dynamic Attention with Global Registers for Video Quality Assessment (DAGR-VQA), the first framework integrating register-token directly into a convolutional backbone for spatio-temporal, dynamic saliency prediction. By embedding learnable register tokens as global context carriers, our model enables dynamic, HVS-inspired attention, producing temporally adaptive saliency maps that track salient regions over time without explicit motion estimation. Our model integrates dynamic saliency maps with RGB inputs, capturing spatial data and analyzing it through a temporal transformer to deliver a perceptually consistent video quality assessment. Comprehensive tests conducted on the LSVQ, KonVid-1k, LIVE-VQC, and YouTube-UGC datasets show that the performance is highly competitive, surpassing the majority of top baselines. Research on ablation studies demonstrates that the integration of register tokens promotes the development of stable and temporally consistent attention mechanisms. Achieving an efficiency of 387.7 FPS at 1080p, DAGR-VQA demonstrates computational performance suitable for real-time applications like multimedia streaming systems.