A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information

• URL: http://arxiv.org/abs/2206.02846v1
• Date: Mon, 6 Jun 2022 18:39:37 GMT
• Title: A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information
• Authors: Matthew Kowal, Mennatullah Siam, Md Amirul Islam, Neil D. B. Bruce, Richard P. Wildes, Konstantinos G. Derpanis
• Abstract summary: We analyse two widely studied tasks, action recognition and video object segmentation. Most examined models are biased toward static information. Certain two-stream architectures with cross-connections show a better balance between the static and dynamic information captured.
• Score: 34.595367958746856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their intermediate representations. For example, while it has been observed that action recognition algorithms are heavily influenced by visual appearance in single static frames, there is no quantitative methodology for evaluating such static bias in the latent representation compared to bias toward dynamic information (e.g. motion). We tackle this challenge by proposing a novel approach for quantifying the static and dynamic biases of any spatiotemporal model. To show the efficacy of our approach, we analyse two widely studied tasks, action recognition and video object segmentation. Our key findings are threefold: (i) Most examined spatiotemporal models are biased toward static information; although, certain two-stream architectures with cross-connections show a better balance between the static and dynamic information captured. (ii) Some datasets that are commonly assumed to be biased toward dynamics are actually biased toward static information. (iii) Individual units (channels) in an architecture can be biased toward static, dynamic or a combination of the two.

Related papers

• Diffusion Priors for Dynamic View Synthesis from Monocular Videos [59.42406064983643]
  Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. We first finetune a pretrained RGB-D diffusion model on the video frames using a customization technique. We distill the knowledge from the finetuned model to a 4D representations encompassing both dynamic and static Neural Radiance Fields.
  arXiv  Detail & Related papers  (2024-01-10T23:26:41Z)
• Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks [34.595367958746856]
  Action recognition, automatic video object segmentation (AVOS) and video instance segmentation (VIS) are studied. Most examined models are biased toward static information. Some datasets that are assumed to be biased toward dynamics are actually biased toward static information.
  arXiv  Detail & Related papers  (2022-11-03T13:17:53Z)
• DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph [59.583555454424]
  We propose a novel disenTangled representation learning framework for discrete-time Dynamic graphs, namely DyTed. We specially design a temporal-clips contrastive learning task together with a structure contrastive learning to effectively identify the time-invariant and time-varying representations respectively.
  arXiv  Detail & Related papers  (2022-10-19T14:34:12Z)
• Spatio-Temporal Relation Learning for Video Anomaly Detection [35.59510027883497]
  Anomaly identification is highly dependent on the relationship between the object and the scene. In this paper, we propose a Spatial-Temporal Relation Learning framework to tackle the video anomaly detection task. Experiments are conducted on three public datasets, and the superior performance over the state-of-the-art methods demonstrates the effectiveness of our method.
  arXiv  Detail & Related papers  (2022-09-27T02:19:31Z)
• STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding [68.96574451918458]
  We propose a framework named STVG, which models visual-linguistic dependencies with a static branch and a dynamic branch. Both the static and dynamic branches are designed as cross-modal transformers. Our proposed method achieved 39.6% vIoU and won the first place in the HC-STVG of the Person in Context Challenge.
  arXiv  Detail & Related papers  (2022-07-06T15:48:58Z)
• Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs [13.436770170612295]
  We study for the first time uncertainty-aware modeling of continuous-time dynamics of interacting objects. Our model infers both independent dynamics and their interactions with reliable uncertainty estimates.
  arXiv  Detail & Related papers  (2022-05-24T08:36:25Z)
• MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras [98.40768911788854]
  We introduce MoCo-Flow, a representation that models the dynamic scene using a 4D continuous time-variant function. At the heart of our work lies a novel optimization formulation, which is constrained by a motion consensus regularization on the motion flow. We extensively evaluate MoCo-Flow on several datasets that contain human motions of varying complexity.
  arXiv  Detail & Related papers  (2021-06-08T16:03:50Z)
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning [87.38675639186405]
  We propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs.
  arXiv  Detail & Related papers  (2021-05-17T15:33:25Z)
• Unified Graph Structured Models for Video Understanding [93.72081456202672]
  We propose a message passing graph neural network that explicitly models relational-temporal relations. We show how our method is able to more effectively model relationships between relevant entities in the scene.
  arXiv  Detail & Related papers  (2021-03-29T14:37:35Z)
• A Gated Fusion Network for Dynamic Saliency Prediction [16.701214795454536]
  Gated Fusion Network for dynamic saliency (GFSalNet) GFSalNet is first deep saliency model capable of making predictions in a dynamic way via gated fusion mechanism. We show that it has a good generalization ability, and moreover, exploits temporal information more effectively via its adaptive fusion scheme.
  arXiv  Detail & Related papers  (2021-02-15T17:18:37Z)

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.