paper-with-me

Papers

Grounded Situation Recognition with Transformers

2021-11-19 · Junhyeong Cho, Youngseok Yoon, Hyeonjun Lee, Suha Kwak

Grounded Situation Recognition (GSR) is the task that not only classifies a salient action (verb), but also predicts entities (nouns) associated with semantic roles and their locations in the given image. Inspired by the remarkable success of Transformers in vision tasks, we propose a GSR model based on a Transformer encoder-decoder architecture. The attention mechanism of our model enables accurate verb classification by capturing high-level semantic feature of an image effectively, and allows the model to flexibly deal with the complicated and image-dependent relations between entities for improved noun classification and localization. Our model is the first Transformer architecture for GSR, and achieves the state of the art in every evaluation metric on the SWiG benchmark. Our code is available at https://github.com/jhcho99/gsrtr .

📄 PDF Abstract BibTeX arXiv:2111.10135

Code (1)

jhcho99/gsrtr 공식 구현 pytorch

Tasks

DecoderGrounded Situation RecognitionImage ClassificationObject DetectionScene UnderstandingSituation RecognitionVisual GroundingVisual Reasoning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Collaborative Transformers for Grounded Situation Recognition

2022-03-30 · CVPR 2022 1 · Junhyeong Cho, Youngseok Yoon, Suha Kwak

Grounded situation recognition is the task of predicting the main activity, entities playing certain roles within the activity, and bounding-box groundings of the entities in the given image. To effectively deal with thi…

Grounded Situation RecognitionImage ClassificationObject DetectionScene Understanding+3

Grounded Situation Recognition

2020-03-26 · ECCV 2020 8 · Sarah Pratt, Mark Yatskar, Luca Weihs, Ali Farhadi 외

We introduce Grounded Situation Recognition (GSR), a task that requires producing structured semantic summaries of images describing: the primary activity, entities engaged in the activity with their roles (e.g. agent, t…

Grounded Situation RecognitionImage RetrievalRetrievalSituation Recognition

From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition

2025-07-19 · Chen Cai, Tianyi Liu, Jianjun Gao, Wenyang Liu 외 arxiv

Recent Multimodal Large Language Models (MLLMs) exhibit strong zero-shot abilities but struggle with complex Grounded Situation Recognition (GSR) and are resource-intensive for edge device deployment. Meanwhile, conventi…

Grounded Situation Recognition

Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer

2024-04-24 · JiaMing Lei, Lin Li, Chunping Wang, Jun Xiao 외

Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recogn…

Grounded Situation RecognitionScene Understanding

XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding

2022-04-15 · ACL 2022 5 · Chan-Jan Hsu, Hung-Yi Lee, Yu Tsao

Transformer-based models are widely used in natural language understanding (NLU) tasks, and multimodal transformers have been effective in visual-language tasks. This study explores distilling visual information from pre…

Natural Language Understanding