Grounded Situation Recognition
1개 벤치마크 · 논문 16편 · 이 태스크의 논문 보기 →
Benchmarks
SWiG
Most implemented
Collaborative Transformers for Grounded Situation Recognition
Commonly Uncommon: Semantic Sparsity in Situation Recognition
Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition
GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
Rethinking the Two-Stage Framework for Grounded Situation Recognition
Papers
From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition
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 RecognitionDynamic Scene Understanding from Vision-Language Representations
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+2Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer
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 UnderstandingOpen Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Grounded Situation Recognition (GSR) is capable of recognizing and interpreting visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the involved entities (roles) depicted in images. In …
DecoderGrounded Situation RecognitionNavigateScene UnderstandingClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition
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 RecognitionGSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
Grounded Situation Recognition (GSR) aims to generate structured semantic summaries of images for "human-like" event understanding. Specifically, GSR task not only detects the salient activity verb (e.g. buying), but als…
Grounded Situation RecognitionImage Captioningobject-detectionObject Detection+1