paper-with-me

Papers

TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition

2018-12-14 · Xiyang Dai, Bharat Singh, Joe Yue-Hei Ng, Larry S. Davis

We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for capturing spatio-temporal information in videos. Since we do not apply 3D convolutions in each layer but only apply temporal aggregation blocks once after each spatial downsampling layer in the network, we significantly reduce the model complexity. The use of dilated convolutions at different resolutions of the network helps in aggregating multi-scale spatio-temporal information efficiently. Experiments show that our model is well suited for dense multi-label action recognition, which is a challenging sub-topic of action recognition that requires predicting multiple action labels in each frame. We outperform state-of-the-art methods by 5% and 3% on the Charades and Multi-THUMOS dataset respectively.

📄 PDF Abstract BibTeX arXiv:1812.06203

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionTemporal Action Localization

Similar Papers 제목 키워드 기반

Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition

2026-05-22 · Yerim So, Jiyeong Kim, Jiwon Yoon, Dongbo Min arxiv

Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained …

Action Recognition

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

2015-07-21 · Serena Yeung, Olga Russakovsky, Ning Jin, Mykhaylo Andriluka 외

Every moment counts in action recognition. A comprehensive understanding of human activity in video requires labeling every frame according to the actions occurring, placing multiple labels densely over a video sequence.…

Action RecognitionRetrievalTemporal Action Localization

DCAN: Improving Temporal Action Detection via Dual Context Aggregation

2021-12-07 · Guo Chen, Yin-Dong Zheng, LiMin Wang, Tong Lu

Temporal action detection aims to locate the boundaries of action in the video. The current method based on boundary matching enumerates and calculates all possible boundary matchings to generate proposals. However, thes…

Action DetectionTemporal Action Localization

Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition

2020-03-31 · CVPR 2020 6 · Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang 외

Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggr…

3D Action RecognitionAction RecognitionLong-range modelingSkeleton Based Action Recognition

An Effective-Efficient Approach for Dense Multi-Label Action Detection

2024-06-10 · Faegheh Sardari, Armin Mustafa, Philip J. B. Jackson, Adrian Hilton

Unlike the sparse label action detection task, where a single action occurs in each timestamp of a video, in a dense multi-label scenario, actions can overlap. To address this challenging task, it is necessary to simulta…

Action Detection