paper-with-me

Papers Situation Recognition

“Situation Recognition” 태그가 달린 논문 15편 · 필터 해제

One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition

2026-04-25 · Balaji Darur, Amanmeet Garg, Makarand Tapaswi arxiv

Video Situation Recognition (VidSitu) addresses the challenging problem of "who did what to whom, with what, how, and where" in a video. It tests thorough video understanding by requiring identification of salient action…

Situation RecognitionVisual Grounding

KIRETT -- A wearable device to support rescue operations using artificial intelligence to improve first aid

2025-09-29 · Johannes Zenkert, Christian Weber, Mubaris Nadeem, Lisa Bender 외 arxiv

This short paper presents first steps in the scientific part of the KIRETT project, which aims to improve first aid during rescue operations using a wearable device. The wearable is used for computer-aided situation reco…

Situation Recognition

The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning

2025-08-29 · Yiming Lin, Yuchen Niu, Shang Wang, Kaizhu Huang 외 arxiv

Context recognition (SR) is a fundamental task in computer vision that aims to extract structured semantic summaries from images by identifying key events and their associated entities. Specifically, given an input image…

Semantic Role LabelingSituation RecognitionMulti-Label Learning

Dynamic Scene Understanding from Vision-Language Representations

2025-01-20 · Shahaf Pruss, Morris Alper, Hadar Averbuch-Elor

Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their intera…

Grounded Situation RecognitionHuman-Human Interaction RecognitionHuman Interaction RecognitionHuman-Object Interaction Detection+2

ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition

2023-07-02 · IEEE WACV 2024 1 · Debaditya Roy, Dhruv Verma, Basura Fernando

Situation Recognition is the task of generating a structured summary of what is happening in an image using an activity verb and the semantic roles played by actors and objects. In this task, the same activity verb can d…

Grounded Situation RecognitionSituation Recognition

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

Rethinking the Two-Stage Framework for Grounded Situation Recognition

2021-12-10 · Meng Wei, Long Chen, Wei Ji, Xiaoyu Yue 외

Grounded Situation Recognition (GSR), i.e., recognizing the salient activity (or verb) category in an image (e.g., buying) and detecting all corresponding semantic roles (e.g., agent and goods), is an essential step towa…

Grounded Situation RecognitionObject RecognitionSituation RecognitionTriplet+1

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…

DecoderGrounded Situation RecognitionImage ClassificationObject Detection+4

Attention-Based Context Aware Reasoning for Situation Recognition

2020-06-01 · CVPR 2020 6 · Thilini Cooray, Ngai-Man Cheung, Wei Lu

Situation Recognition (SR) is a fine-grained action recognition task where the model is expected to not only predict the salient action of the image, but also predict values of all associated semantic roles of the action…

Action RecognitionFine-grained Action RecognitionGrounded Situation RecognitionQuestion Answering+4

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

Mixture-Kernel Graph Attention Network for Situation Recognition

2019-10-01 · ICCV 2019 10 · Mohammed Suhail, Leonid Sigal

Understanding images beyond salient actions involves reasoning about scene context, objects, and the roles they play in the captured event. Situation recognition has recently been introduced as the task of jointly reason…

Graph AttentionGraph Neural NetworkGrounded Situation RecognitionSituation Recognition

Situation Recognition with Graph Neural Networks

2017-08-14 · ICCV 2017 10 · Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia 외

We address the problem of recognizing situations in images. Given an image, the task is to predict the most salient verb (action), and fill its semantic roles such as who is performing the action, what is the source and …

Grounded Situation RecognitionSituation Recognition

Recurrent Models for Situation Recognition

2017-03-18 · ICCV 2017 10 · Arun Mallya, Svetlana Lazebnik

This work proposes Recurrent Neural Network (RNN) models to predict structured 'image situations' -- actions and noun entities fulfilling semantic roles related to the action. In contrast to prior work relying on Conditi…

Grounded Situation RecognitionHuman-Object Interaction DetectionImage CaptioningPrediction+1

Commonly Uncommon: Semantic Sparsity in Situation Recognition

2016-12-03 · CVPR 2017 7 · Mark Yatskar, Vicente Ordonez, Luke Zettlemoyer, Ali Farhadi

Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This pa…

Grounded Situation RecognitionSituation RecognitionStructured Prediction

Situation Recognition: Visual Semantic Role Labeling for Image Understanding

2016-06-01 · CVPR 2016 6 · Mark Yatskar, Luke Zettlemoyer, Ali Farhadi

This paper introduces situation recognition, the problem of producing a concise summary of the situation an image depicts including: (1) the main activity (e.g., clipping), (2) the participating actors, objects, substanc…

Activity RecognitionGrounded Situation RecognitionSemantic Role LabelingSituation Recognition+1
1–15 / 15