paper-with-me

Papers

Blockwise Temporal-Spatial Pathway Network

2022-08-05 · SeulGi Hong, Min-Kook Choi

Algorithms for video action recognition should consider not only spatial information but also temporal relations, which remains challenging. We propose a 3D-CNN-based action recognition model, called the blockwise temporal-spatial path-way network (BTSNet), which can adjust the temporal and spatial receptive fields by multiple pathways. We designed a novel model inspired by an adaptive kernel selection-based model, which is an architecture for effective feature encoding that adaptively chooses spatial receptive fields for image recognition. Expanding this approach to the temporal domain, our model extracts temporal and channel-wise attention and fuses information on various candidate operations. For evaluation, we tested our proposed model on UCF-101, HMDB-51, SVW, and Epic-Kitchen datasets and showed that it generalized well without pretraining. BTSNet also provides interpretable visualization based on spatiotemporal channel-wise attention. We confirm that the blockwise temporal-spatial pathway supports a better representation for 3D convolutional blocks based on this visualization.

📄 PDF Abstract BibTeX arXiv:2208.03040

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionTemporal Action Localization

Similar Papers 제목 키워드 기반

Gesture Recognition with a Skeleton-Based Keyframe Selection Module

2021-12-03 · Yunsoo Kim, Hyun Myung

We propose a bidirectional consecutively connected two-pathway network (BCCN) for efficient gesture recognition. The BCCN consists of two pathways: (i) a keyframe pathway and (ii) a temporal-attention pathway. The keyfra…

Gesture Recognition

NeuroPath: Brain-Inspired Dual-Pathway Graph Convolutional Networks for Skeleton-Based Action Recognition

2026-08-18 · Kanglei Zhou, Ruizhi Cai, Hubert P. H. Shum, Frederick W. B. Li 외 arxiv

Skeleton-based action recognition aims to recognize human actions from sequences of human joint coordinates. Most existing Spatial-Temporal Graph Convolutional Networks (STGCNs) have achieved promising results by modelin…

Action Recognition

Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings

2025-08-18 · Taous Iatariene, Alexandre Guérin, Romain Serizel arxiv

Speaker embeddings are promising identity-related features that can enhance the identity assignment performance of a tracking system by leveraging its spatial predictions, i.e, by performing identity reassignment. Common…

Knowledge Distillation

STCNet: Spatio-Temporal Cross Network for Industrial Smoke Detection

2020-11-10 · Yichao Cao, Qingfei Tang, Xiaobo Lu, Fan Li 외

Industrial smoke emissions present a serious threat to natural ecosystems and human health. Prior works have shown that using computer vision techniques to identify smoke is a low cost and convenient method. However, ind…

Depth-Wise Representation Development Under Blockwise Self-Supervised Learning for Video Vision Transformers

2026-01-14 · Jonas Römer, Timo Dickscheid arxiv

End-to-end backpropagation couples all layers through a global error signal, enabling coordinated learning but requiring long-range credit assignment. Motivated by recent progress in blockwise self-supervised learning (B…

Self-Supervised Learning