Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer

• URL: http://arxiv.org/abs/2604.06783v1
• Date: Wed, 08 Apr 2026 07:52:28 GMT
• Title: Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer
• Abstract summary: Recently Transformer has made significant progress in various vision tasks.<n>We argue that the importance of temporal and spatial information varies across different time scales.<n>We propose a dual-path network called the Overall Glance and Glance Gaze Transformer.
• Score: 9.235058796055139
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, Transformer has made significant progress in various vision tasks. To balance computation and efficiency in video tasks, recent works heavily rely on factorized or window-based self-attention. However, these approaches split spatiotemporal correlations between regions of interest in videos, limiting the models' ability to capture motion and long-range dependencies. In this paper, we argue that, similar to the human visual system, the importance of temporal and spatial information varies across different time scales, and attention is allocated sparsely over time through glance and gaze behavior. Is equal consideration of time and space crucial for success in video tasks? Motivated by this understanding, we propose a dual-path network called the Overall Glance and Refined Gaze (OG-ReG) Transformer. The Glance path extracts coarse-grained overall spatiotemporal information, while the Gaze path supplements the Glance path by providing local details. Our model achieves state-of-the-art results on the Kinetics-400, Something-Something v2, and Diving-48, demonstrating its competitive performance. The code will be available at https://github.com/linuxsino/OG-ReG.

Related papers

• CGTGait: Collaborative Graph and Transformer for Gait Emotion Recognition [9.539530757201206]
  Skeleton-based gait emotion recognition has received significant attention due to its wide-ranging applications.<n>In this paper, we propose textbfCGTGait a framework that collaboratively integrates graph convolution and transformers.<n>We evaluate our method on two widely used datasets, Emotion-Gait and ELMD.
  arXiv  Detail & Related papers  (2025-09-20T10:48:51Z)
• TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers [2.2120851074630177]
  We develop a graph embedding model with uncertainty quantification, TransformerG2G, to learn temporal dynamics of temporal graphs. Our experiments demonstrate that the proposed TransformerG2G model outperforms conventional multi-step methods. By examining the attention weights, we can uncover temporal dependencies, identify influential elements, and gain insights into the complex interactions within the graph structure.
  arXiv  Detail & Related papers  (2023-07-05T18:34:22Z)
• Efficient Modelling Across Time of Human Actions and Interactions [92.39082696657874]
  We argue that current fixed-sized-temporal kernels in 3 convolutional neural networks (CNNDs) can be improved to better deal with temporal variations in the input. We study how we can better handle between classes of actions, by enhancing their feature differences over different layers of the architecture. The proposed approaches are evaluated on several benchmark action recognition datasets and show competitive results.
  arXiv  Detail & Related papers  (2021-10-05T15:39:11Z)
• JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting [53.28477676794658]
  unsupervised motion in videos has seen substantial advancements through the use of deep neural networks. We introduce JOKR - a JOint Keypoint Representation that handles both the source and target videos, without requiring any object prior or data collection. We evaluate our method both qualitatively and quantitatively, and demonstrate that our method handles various cross-domain scenarios, such as different animals, different flowers, and humans.
  arXiv  Detail & Related papers  (2021-06-17T17:32:32Z)
• Glance-and-Gaze Vision Transformer [13.77016463781053]
  We propose a new vision Transformer, named Glance-and-Gaze Transformer (GG-Transformer) It is motivated by the Glance and Gaze behavior of human beings when recognizing objects in natural scenes. We empirically demonstrate our method achieves consistently superior performance over previous state-of-the-art Transformers.
  arXiv  Detail & Related papers  (2021-06-04T06:13:47Z)
• Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos [78.45050529204701]
  We propose a novel framework to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation. CTL utilizes a CNN backbone and a key-points estimator to extract semantic local features from human body. It explores a context-reinforced topology to construct multi-scale graphs by considering both global contextual information and physical connections of human body.
  arXiv  Detail & Related papers  (2021-04-15T14:32:12Z)
• Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation [79.98992138865042]
  We present an augmented transformer with adaptive graph network (ATAG) to exploit both long-range and local temporal contexts for TAPG. Specifically, we enhance the vanilla transformer by equipping a snippet actionness loss and a front block, dubbed augmented transformer. An adaptive graph convolutional network (GCN) is proposed to build local temporal context by mining the position information and difference between adjacent features.
  arXiv  Detail & Related papers  (2021-03-30T02:01:03Z)
• Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition [14.07119502083967]
  Driver's activities are different since they are executed by the same subject with similar body parts movements, resulting in subtle changes. Our model is named Coarse Temporal Attention Network (CTA-Net), in which coarse temporal branches are introduced in a trainable glimpse. The model then uses an innovative attention mechanism to generate high-level action specific contextual information for activity recognition.
  arXiv  Detail & Related papers  (2021-01-17T10:15:37Z)
• DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection [78.04869214450963]
  We propose a novel dynamic temporal-temporal network (DSNet) for more effective fusion of temporal and spatial information. We show that the proposed method achieves superior performance than state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2020-12-09T06:42:30Z)
• Gravitational Models Explain Shifts on Human Visual Attention [80.76475913429357]
  Visual attention refers to the human brain's ability to select relevant sensory information for preferential processing. Various methods to estimate saliency have been proposed in the last three decades. We propose a gravitational model (GRAV) to describe the attentional shifts.
  arXiv  Detail & Related papers  (2020-09-15T10:12:41Z)

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.