Seeing 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 recognition (GSR) requires the model not only to classify salient activity (verb) in the image, but also to detect all semantic roles that participate in the action. This complex task usually involves three steps: verb recognition, semantic role grounding, and noun recognition. Directly employing class-based prompts with VLMs and grounding models for this task suffers from several limitations, e.g., it struggles to distinguish ambiguous verb concepts, accurately localize roles with fixed verb-centric template1 input, and achieve context-aware noun predictions. In this paper, we argue that these limitations stem from the mode's poor understanding of verb/noun classes. To this end, we introduce a new approach for zero-shot GSR via Language EXplainer (LEX), which significantly boosts the model's comprehensive capabilities through three explainers: 1) verb explainer, which generates general verb-centric descriptions to enhance the discriminability of different verb classes; 2) grounding explainer, which rephrases verb-centric templates for clearer understanding, thereby enhancing precise semantic role localization; and 3) noun explainer, which creates scene-specific noun descriptions to ensure context-aware noun recognition. By equipping each step of the GSR process with an auxiliary explainer, LEX facilitates complex scene understanding in real-world scenarios. Our extensive validations on the SWiG dataset demonstrate LEX's effectiveness and interoperability in zero-shot GSR.
Code (0)
등록된 구현이 없습니다.
Tasks
Grounded Situation RecognitionScene UnderstandingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation
Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However, they rely on a significant amount of la…
Data-to-Text GenerationGeneral KnowledgeKG-to-Text GenerationText Generation+1VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., w…
Transfer LearningWord EmbeddingsZero-Shot LearningLearning without Seeing nor Knowing: Towards Open Zero-Shot Learning
In Generalized Zero-Shot Learning (GZSL), unseen categories (for which no visual data are available at training time) can be predicted by leveraging their class embeddings (e.g., a list of attributes describing them) tog…
Generalized Zero-Shot LearningZero-Shot LearningZero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment
Wi-Fi-based human activity recognition has advanced substantially, but most existing methods assume a closed set of activities and require labeled Wi-Fi samples for every target class, limiting their ability to recognize…
Human Activity RecognitionSeeingSounds: Learning Audio-to-Visual Alignment via Text
We introduce SeeingSounds, a lightweight and modular framework for audio-to-image generation that leverages the interplay between audio, language, and vision-without requiring any paired audio-visual data or training on …
Image Generation