A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition

• URL: http://arxiv.org/abs/2401.00409v1
• Date: Sun, 31 Dec 2023 06:46:46 GMT
• Title: A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition
• Authors: Ruoqi Yin, Jianqin Yin
• Abstract summary: We propose a Two-stream Hybrid CNN-Transformer Network (THCT-Net) It exploits the local specificity of CNN and models global dependencies through the Transformer. We show that the proposed method can better comprehend and infer the meaning and context of various actions, outperforming state-of-the-art methods.
• Score: 6.490564374810672
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human Interaction Recognition is the process of identifying interactive actions between multiple participants in a specific situation. The aim is to recognise the action interactions between multiple entities and their meaning. Many single Convolutional Neural Network has issues, such as the inability to capture global instance interaction features or difficulty in training, leading to ambiguity in action semantics. In addition, the computational complexity of the Transformer cannot be ignored, and its ability to capture local information and motion features in the image is poor. In this work, we propose a Two-stream Hybrid CNN-Transformer Network (THCT-Net), which exploits the local specificity of CNN and models global dependencies through the Transformer. CNN and Transformer simultaneously model the entity, time and space relationships between interactive entities respectively. Specifically, Transformer-based stream integrates 3D convolutions with multi-head self-attention to learn inter-token correlations; We propose a new multi-branch CNN framework for CNN-based streams that automatically learns joint spatio-temporal features from skeleton sequences. The convolutional layer independently learns the local features of each joint neighborhood and aggregates the features of all joints. And the raw skeleton coordinates as well as their temporal difference are integrated with a dual-branch paradigm to fuse the motion features of the skeleton. Besides, a residual structure is added to speed up training convergence. Finally, the recognition results of the two branches are fused using parallel splicing. Experimental results on diverse and challenging datasets, demonstrate that the proposed method can better comprehend and infer the meaning and context of various actions, outperforming state-of-the-art methods.

Related papers

• Interaction-Guided Two-Branch Image Dehazing Network [1.26404863283601]
  Image dehazing aims to restore clean images from hazy ones. CNNs and Transformers have demonstrated exceptional performance in local and global feature extraction. We propose a novel dual-branch image dehazing framework that guides CNN and Transformer components interactively.
  arXiv  Detail & Related papers  (2024-10-14T03:21:56Z)
• Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition [45.0131792009999]
  We propose a point cloud-based network named Two-stream Multi-level Dynamic Point Transformer for two-person interaction recognition. Our model addresses the challenge of recognizing two-person interactions by incorporating local-region spatial information, appearance information, and motion information. Our network outperforms state-of-the-art approaches in most standard evaluation settings.
  arXiv  Detail & Related papers  (2023-07-22T03:51:32Z)
• Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition [8.513434732050749]
  We propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations.
  arXiv  Detail & Related papers  (2023-07-14T16:51:25Z)
• Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification [91.56939957189505]
  We propose a novel spatial-temporal complementary learning framework named Deeply-Coupled Convolution-Transformer (DCCT) for high-performance video-based person Re-ID. Our framework could attain better performances than most state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-27T12:16:44Z)
• Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks [11.66009967197084]
  We propose a novel Contrastive GCN-Transformer Network (ConGT) which fuses the spatial and temporal modules in a parallel way. We conduct experiments on three benchmark datasets, which demonstrate that our model achieves state-of-the-art performance in action recognition.
  arXiv  Detail & Related papers  (2023-01-27T02:12:08Z)
• Hierarchical Local-Global Transformer for Temporal Sentence Grounding [58.247592985849124]
  This paper studies the multimedia problem of temporal sentence grounding. It aims to accurately determine the specific video segment in an untrimmed video according to a given sentence query.
  arXiv  Detail & Related papers  (2022-08-31T14:16:56Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Dense Interaction Learning for Video-based Person Re-identification [75.03200492219003]
  We propose a hybrid framework, Dense Interaction Learning (DenseIL), to tackle video-based person re-ID difficulties. DenseIL contains a CNN encoder and a Dense Interaction (DI) decoder. Our experiments consistently and significantly outperform all the state-of-the-art methods on multiple standard video-based re-ID datasets.
  arXiv  Detail & Related papers  (2021-03-16T12:22:08Z)
• Learning Asynchronous and Sparse Human-Object Interaction in Videos [56.73059840294019]
  Asynchronous-Sparse Interaction Graph Networks (ASSIGN) is able to automatically detect the structure of interaction events associated with entities in a video scene. ASSIGN is tested on human-object interaction recognition and shows superior performance in segmenting and labeling of human sub-activities and object affordances from raw videos.
  arXiv  Detail & Related papers  (2021-03-03T23:43:55Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

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.