paper-with-me

Papers

Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos

2022-09-21 · Tomás Crisol, Joel Ermantraut, Adrián Rostagno, Santiago L. Aggio, Javier Iparraguirre

During recent years transformers architectures have been growing in popularity. Modulated Detection Transformer (MDETR) is an end-to-end multi-modal understanding model that performs tasks such as phase grounding, referring expression comprehension, referring expression segmentation, and visual question answering. One remarkable aspect of the model is the capacity to infer over classes that it was not previously trained for. In this work we explore the use of MDETR in a new task, action detection, without any previous training. We obtain quantitative results using the Atomic Visual Actions dataset. Although the model does not report the best performance in the task, we believe that it is an interesting finding. We show that it is possible to use a multi-modal model to tackle a task that it was not designed for. Finally, we believe that this line of research may lead into the generalization of MDETR in additional downstream tasks.

📄 PDF Abstract BibTeX arXiv:2209.10126

Code (1)

bhi-research/ava_mdetr 공식 구현 pytorch

Tasks

Action DetectionAction RecognitionAction Recognition In VideosQuestion AnsweringReferring ExpressionReferring Expression ComprehensionReferring Expression SegmentationVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

2023-07-23 · Yiming Cui, Linjie Yang, Haichao Yu

Transformer-based detection and segmentation methods use a list of learned detection queries to retrieve information from the transformer network and learn to predict the location and category of one specific object from…

Instance SegmentationObjectobject-detectionObject Detection+4

QUEST: A robust attention formulation using query-modulated spherical attention

2026-03-31 · Hariprasath Govindarajan, Per Sidén, Jacob Roll, Fredrik Lindsten arxiv

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot p…

Band-Attention Modulated RetNet for Face Forgery Detection

2024-04-09 · Zhida Zhang, Jie Cao, Wenkui Yang, Qihang Fan 외

The transformer networks are extensively utilized in face forgery detection due to their scalability across large datasets.Despite their success, transformers face challenges in balancing the capture of global context, w…

Fast Convergence of DETR with Spatially Modulated Co-Attention

2021-01-19 · Peng Gao, Minghang Zheng, Xiaogang Wang, Jifeng Dai 외

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However,…

Decoderobject-detectionObject Detection

Fast Convergence of DETR with Spatially Modulated Co-Attention

2021-08-05 · ICCV 2021 10 · Peng Gao, Minghang Zheng, Xiaogang Wang, Jifeng Dai 외

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However,…

Decoderobject-detectionObject Detection