AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition

• URL: http://arxiv.org/abs/2405.02538v1
• Date: Sat, 4 May 2024 01:53:22 GMT
• Title: AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition
• Authors: Meiqi Cao, Rui Yan, Xiangbo Shu, Guangzhao Dai, Yazhou Yao, Guo-Sen Xie,
• Abstract summary: Panoramic Activity Recognition (PAR) aims to identify multi-granularity behaviors performed by multiple persons in panoramic scenes. Previous methods rely on manually annotated detection boxes in training and inference, hindering further practical deployment. We propose a novel Adapt-Focused bi-Propagating Prototype learning (AdaFPP) framework to jointly recognize individual, group, and global activities in panoramic activity scenes.
• Score: 51.24321348668037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Panoramic Activity Recognition (PAR) aims to identify multi-granularity behaviors performed by multiple persons in panoramic scenes, including individual activities, group activities, and global activities. Previous methods 1) heavily rely on manually annotated detection boxes in training and inference, hindering further practical deployment; or 2) directly employ normal detectors to detect multiple persons with varying size and spatial occlusion in panoramic scenes, blocking the performance gain of PAR. To this end, we consider learning a detector adapting varying-size occluded persons, which is optimized along with the recognition module in the all-in-one framework. Therefore, we propose a novel Adapt-Focused bi-Propagating Prototype learning (AdaFPP) framework to jointly recognize individual, group, and global activities in panoramic activity scenes by learning an adapt-focused detector and multi-granularity prototypes as the pretext tasks in an end-to-end way. Specifically, to accommodate the varying sizes and spatial occlusion of multiple persons in crowed panoramic scenes, we introduce a panoramic adapt-focuser, achieving the size-adapting detection of individuals by comprehensively selecting and performing fine-grained detections on object-dense sub-regions identified through original detections. In addition, to mitigate information loss due to inaccurate individual localizations, we introduce a bi-propagation prototyper that promotes closed-loop interaction and informative consistency across different granularities by facilitating bidirectional information propagation among the individual, group, and global levels. Extensive experiments demonstrate the significant performance of AdaFPP and emphasize its powerful applicability for PAR.

Related papers

• Spatio-Temporal Context Prompting for Zero-Shot Action Detection [13.22912547389941]
  We propose a method which can effectively leverage the rich knowledge of visual-language models to perform Person-Context Interaction. To address the challenge of recognizing distinct actions by multiple people at the same timestamp, we design the Interest Token Spotting mechanism. Our method achieves superior results compared to previous approaches and can be further extended to multi-action videos.
  arXiv  Detail & Related papers  (2024-08-28T17:59:05Z)
• MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition [2.1794550051087995]
  We propose a model called MPT-PAR that considers both the unique characteristics of each task and the synergies between different tasks simultaneously. Our method achieved granularity and an overall F1 score of 47.5% on the JRDB-PAR dataset.
  arXiv  Detail & Related papers  (2024-08-01T09:42:44Z)
• GOOD: Towards Domain Generalized Orientated Object Detection [39.76969237020444]
  Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution. We propose the task of domain generalized oriented object detection, which intends to explore the generalization of oriented object detectors on arbitrary unseen target domains.
  arXiv  Detail & Related papers  (2024-02-20T07:12:22Z)
• Aligning and Prompting Everything All at Once for Universal Visual Perception [79.96124061108728]
  APE is a universal visual perception model for aligning and prompting everything all at once in an image to perform diverse tasks. APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection. Experiments on over 160 datasets demonstrate that APE outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-04T18:59:50Z)
• Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems [61.11799513362704]
  We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
  arXiv  Detail & Related papers  (2023-03-03T02:07:40Z)
• Towards Effective Image Manipulation Detection with Proposal Contrastive Learning [61.5469708038966]
  We propose Proposal Contrastive Learning (PCL) for effective image manipulation detection. Our PCL consists of a two-stream architecture by extracting two types of global features from RGB and noise views respectively. Our PCL can be easily adapted to unlabeled data in practice, which can reduce manual labeling costs and promote more generalizable features.
  arXiv  Detail & Related papers  (2022-10-16T13:30:13Z)
• Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning [51.03781020616402]
  Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications. We propose a few-shot fine-grained action recognition problem, aiming to recognize novel fine-grained actions with only few samples given for each class. Although progress has been made in coarse-grained actions, existing few-shot recognition methods encounter two issues handling fine-grained actions.
  arXiv  Detail & Related papers  (2021-08-15T02:21:01Z)
• Adaptive Object Detection with Dual Multi-Label Prediction [78.69064917947624]
  We propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection. The model exploits multi-label prediction to reveal the object category information in each image. We introduce a prediction consistency regularization mechanism to assist object detection.
  arXiv  Detail & Related papers  (2020-03-29T04:23:22Z)

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.