paper-with-me

Papers

QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024

2024-07-04 · Zeyun Zhong, Manuel Martin, Frederik Diederichs, Juergen Beyerer

This report presents a novel Mamba-based encoder-decoder architecture, QueryMamba, featuring an integrated verb-noun interaction module that utilizes a statistical verb-noun co-occurrence matrix to enhance video action forecasting. This architecture not only predicts verbs and nouns likely to occur based on historical data but also considers their joint occurrence to improve forecast accuracy. The efficacy of this approach is substantiated by experimental results, with the method achieving second place in the Ego4D LTA challenge and ranking first in noun prediction accuracy.

📄 PDF Abstract BibTeX arXiv:2407.04184

Code (0)

등록된 구현이 없습니다.

Tasks

Action AnticipationDecoderLong Term Action AnticipationMamba

Similar Papers 제목 키워드 기반

MambaVesselNet++: A Hybrid CNN-Mamba Architecture for Medical Image Segmentation

2025-07-26 · Qing Xu, Yanming Chen, Yue Li, Ziyu Liu 외 arxiv

Medical image segmentation plays an important role in computer-aided diagnosis. Traditional convolution-based U-shape segmentation architectures are usually limited by the local receptive field. Existing vision transform…

Medical Image SegmentationInstance Segmentation

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

2025-02-18 · Bencheng Liao, Hongyuan Tao, Qian Zhang, Tianheng Cheng 외

Recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance but face deployment challenges due to their quadratic computational complexity, growing Key-Value cache requirements, and reliance on s…

DecoderGPUMambaState Space Models

DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling

2025-06-05 · Hangyu Ji

Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence model…

AnatomyBrain Tumor SegmentationDecoderImage Segmentation+7

Vision Mamba-based autonomous crack segmentation on concrete, asphalt, and masonry surfaces

2024-06-24 · Zhaohui Chen, Elyas Asadi Shamsabadi, Sheng Jiang, Luming Shen 외

Convolutional neural networks (CNNs) and Transformers have shown advanced accuracy in crack detection under certain conditions. Yet, the fixed local attention can compromise the generalisation of CNNs, and the quadratic …

Crack SegmentationDecoderMamba

Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation

2024-02-07 · Ziyang Wang, Jian-Qing Zheng, Yichi Zhang, Ge Cui 외

In recent advancements in medical image analysis, Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have set significant benchmarks. While the former excels in capturing local features through its convolu…

Cardiac SegmentationComputational EfficiencyDecoderImage Segmentation+5