paper-with-me

홈 › Papers

Adaptive Perception Transformer for Temporal Action Localization

2022-08-25 · Yizheng Ouyang, Tianjin Zhang, Weibo Gu, Hongfa Wang

Temporal action localization aims to predict the boundary and category of each action instance in untrimmed long videos. Most of previous methods based on anchors or proposals neglect the global-local context interaction in entire video sequences. Besides, their multi-stage designs cannot generate action boundaries and categories straightforwardly. To address the above issues, this paper proposes a end-to-end model, called Adaptive Perception transformer (AdaPerFormer for short). Specifically, AdaPerFormer explores a dual-branch attention mechanism. One branch takes care of the global perception attention, which can model entire video sequences and aggregate global relevant contexts. While the other branch concentrates on the local convolutional shift to aggregate intra-frame and inter-frame information through our bidirectional shift operation. The end-to-end nature produces the boundaries and categories of video actions without extra steps. Extensive experiments together with ablation studies are provided to reveal the effectiveness of our design. Our method obtains competitive performance on the THUMOS14 and ActivityNet-1.3 dataset.

📄 PDF Abstract BibTeX arXiv:2208.11908

Code (0)

등록된 구현이 없습니다.

Tasks

Action LocalizationTemporal Action Localization

Similar Papers 제목 키워드 기반

Few-Shot Temporal Action Localization with Query Adaptive Transformer

2021-10-20 · Sauradip Nag, Xiatian Zhu, Tao Xiang

Existing temporal action localization (TAL) works rely on a large number of training videos with exhaustive segment-level annotation, preventing them from scaling to new classes. As a solution to this problem, few-shot T…

Action LocalizationAction SegmentationFew Shot Temporal Action LocalizationFine-Grained Action Detection+3

UniHead: Unifying Multi-Perception for Detection Heads

2023-09-23 · Hantao Zhou, Rui Yang, Yachao Zhang, Haoran Duan 외

The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used parallel head often lacks omni perceptual c…

IONext: Unlocking the Next Era of Inertial Odometry

2025-07-23 · Shanshan Zhang, Qi Zhang, Siyue Wang, Tianshui Wen 외 arxiv

Researchers have increasingly adopted Transformer-based models for inertial odometry. While Transformers excel at modeling long-range dependencies, their limited sensitivity to local, fine-grained motion variations and l…

Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception

2023-07-26 · ICCV 2023 1 · Kun Yang, Dingkang Yang, Jingyu Zhang, Mingcheng Li 외

Multi-agent collaborative perception as a potential application for vehicle-to-everything communication could significantly improve the perception performance of autonomous vehicles over single-agent perception. However,…

3D Object DetectionAutonomous Vehiclesobject-detectionObject Detection

Temporal Action Localization with Enhanced Instant Discriminability

2023-09-11 · Dingfeng Shi, Qiong Cao, Yujie Zhong, Shan An 외

Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action b…

Action DetectionAction LocalizationTemporal Action Localization