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

• URL: http://arxiv.org/abs/2601.11045v1
• Date: Fri, 16 Jan 2026 07:25:16 GMT
• Title: Convolutions Need Registers Too: HVS-Inspired Dynamic Attention for Video Quality Assessment
• Abstract summary: 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 dynamic video saliency prediction.<n>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.
• Score: 1.7188280334580195
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• StreamAV-Bench: A Comprehensive Benchmark for Streaming Audio-Video Generation [48.448082116311156]
  StreamAV-Bench is the first comprehensive benchmark tailored for streaming audio-video generation.<n>Our analysis reveals that current models suffer from temporal drift in progressive generation and responsiveness bottlenecks during interactive control.<n>Based on a comprehensive failure analysis, we share insights to advance the development of native joint audio-video streaming models.
  arXiv  Detail & Related papers  (2026-08-26T19:16:24Z)
• Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets [71.53287557600177]
  We take the first major step toward establishing event-based anomaly detection as a unified research direction.<n>We first construct multiple eventstream based benchmarks for video anomaly detection, featuring synchronized event and RGB recordings.<n>We then propose an EVent-centric Video Anomaly Detection framework, namely EWAD, with three key innovations.
  arXiv  Detail & Related papers  (2026-03-26T03:33:33Z)
• Learning Spatio-Temporal Feature Representations for Video-Based Gaze Estimation [50.05866669110754]
  Video-based gaze estimation methods aim to capture the inherently temporal dynamics of human eye gaze from multiple image frames.<n>We propose the Spatio-Temporal Gaze Network (ST-Gaze), a model that combines a CNN backbone with dedicated channel attention and self-attention modules.<n>We show that ST-Gaze achieves state-of-the-art performance both with and without person-specific adaptation.
  arXiv  Detail & Related papers  (2025-12-19T15:15:58Z)
• Q-Save: Towards Scoring and Attribution for Generated Video Evaluation [65.83319736145869]
  We present Q-Save, a new benchmark dataset and model for holistic evaluation of AI-generated video (AIGV) quality.<n>The dataset contains near 10000 videos, each annotated with a scalar mean opinion score (MOS) and fine-grained attribution labels.<n>We propose a unified evaluation model that jointly performs quality scoring and attribution-based explanation.
  arXiv  Detail & Related papers  (2025-11-24T07:00:21Z)
• Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence [70.2803680525165]
  We introduce Open-o3 Video, a non-agent framework that integrates explicit evidence into video reasoning.<n>The model highlights key objects and bounding boxes alongside its answers, allowing reasoning to be grounded in concrete visual observations.<n>On V-STAR benchmark, Open-o3 Video achieves state-of-the-art performance, raising mAM by 14.4% and mL timestamp by 24.2%.
  arXiv  Detail & Related papers  (2025-10-23T14:05:56Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• Emergent Temporal Correspondences from Video Diffusion Transformers [30.83001895223298]
  We introduce DiffTrack, the first quantitative analysis framework designed to answer this question.<n>Our analysis reveals that query-key similarities in specific, but not all, layers play a critical role in temporal matching.<n>We extend our findings to motion-enhanced video generation with a novel guidance method that improves temporal consistency of generated videos without additional training.
  arXiv  Detail & Related papers  (2025-06-20T17:59:55Z)
• Towards Generalized Video Quality Assessment: A Weak-to-Strong Learning Paradigm [76.63001244080313]
  Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception.<n>The dominant VQA paradigm relies on supervised training with human-labeled datasets.<n>We explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on large-scale human-labeled datasets.
  arXiv  Detail & Related papers  (2025-05-06T15:29:32Z)
• Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling [7.3949576464066]
  We propose a deep learning framework designed to significantly optimize bandwidth for motion-transfer-enabled video applications.<n>To capture complex motion effectively, we utilize the First Order Motion Model (FOMM), which encodes dynamic objects by detecting keypoints.<n>We validate our results across three datasets for video animation and reconstruction using the following metrics: Mean Absolute Error, Joint Embedding Predictive Architecture Embedding Distance, Structural Similarity Index, and Average Pair-wise Displacement.
  arXiv  Detail & Related papers  (2025-04-07T22:21:54Z)
• MAUCell: An Adaptive Multi-Attention Framework for Video Frame Prediction [0.0]
  We introduce the Multi-Attention Unit (MAUCell) which combines Generative Adrative Networks (GANs) and attention mechanisms to improve video prediction.<n>The new design system maintains equilibrium between temporal continuity and spatial accuracy to deliver reliable video prediction.
  arXiv  Detail & Related papers  (2025-01-28T14:52:10Z)
• CLIPVQA:Video Quality Assessment via CLIP [56.94085651315878]
  We propose an efficient CLIP-based Transformer method for the VQA problem ( CLIPVQA) The proposed CLIPVQA achieves new state-of-the-art VQA performance and up to 37% better generalizability than existing benchmark VQA methods.
  arXiv  Detail & Related papers  (2024-07-06T02:32:28Z)
• CONVIQT: Contrastive Video Quality Estimator [63.749184706461826]
  Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner. Our results indicate that compelling representations with perceptual bearing can be obtained using self-supervised learning.
  arXiv  Detail & Related papers  (2022-06-29T15:22:01Z)
• RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content [44.03188436272383]
  We introduce an effective and efficient video quality model for content, which we dub the Rapid and Accurate Video Quality Evaluator (RAPIQUE) RAPIQUE combines and leverages the advantages of both quality-aware scene statistics features and semantics-aware deep convolutional features. Our experimental results on recent large-scale video quality databases show that RAPIQUE delivers top performances on all the datasets at a considerably lower computational expense.
  arXiv  Detail & Related papers  (2021-01-26T17:23:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.