paper-with-me

홈 › Papers

STAMP: Spatial-Temporal Adapter with Multi-Head Pooling

2025-11-13 · Brad Shook, Abby Turner, Jieshi Chen, Michał Wiliński, Mononito Goswami, Jonathan Elmer, Artur Dubrawski arxiv

Time series foundation models (TSFMs) pretrained on data from multiple domains have shown strong performance on diverse modeling tasks. Various efforts have been made to develop foundation models specific to electroencephalography (EEG) data, which records brain electrical activity as time series. However, no comparative analysis of EEG-specific foundation models (EEGFMs) versus general TSFMs has been performed on EEG-specific tasks. We introduce a novel Spatial-Temporal Adapter with Multi-Head Pooling (STAMP), which leverages univariate embeddings produced by a general TSFM, implicitly models spatial-temporal characteristics of EEG data, and achieves performance comparable to state-of-the-art EEGFMs. A comprehensive analysis is performed on 8 benchmark datasets of clinical tasks using EEG for classification, along with ablation studies. Our proposed adapter is lightweight in trainable parameters and flexible in the inputs it can accommodate, supporting easy modeling of EEG data using TSFMs.

📄 PDF Abstract BibTeX arXiv:2511.10848

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding

2025-04-10 · Henghao Zhao, Ge-Peng Ji, Rui Yan, Huan Xiong 외

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps…

Instruction FollowingVideo Understanding

T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding

2026-03-07 · Chaohong Guo, Yihan He, Yongwei Nie, Fei Ma 외 arxiv

Video Temporal Grounding (VTG) aims to localize the video segment that corresponds to a natural language query, which requires a comprehensive understanding of complex temporal dynamics. Existing Vision-LMMs typically pe…

Temporal Sequences

D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition

2023-12-03 · Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian

Adapting large pre-trained image models to few-shot action recognition has proven to be an effective and efficient strategy for learning robust feature extractors, which is essential for few-shot learning. Typical fine-t…

Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionFew-Shot Learning

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data

2023-09-11 · Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu 외

Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving…

graph constructionGraph Neural NetworkTime Series

Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

2023-04-03 · ICCV 2023 1 · Zhuofan Zong, Dongzhi Jiang, Guanglu Song, Zeyue Xue 외

In this paper, we propose a new paradigm, named Historical Object Prediction (HoP) for multi-view 3D detection to leverage temporal information more effectively. The HoP approach is straightforward: given the current tim…

3D Object DetectionObject