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

Jiaming Lei, Lin Li, Chunping Wang, Jun Xiao, Long Chen

Abstract: 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 template input, and achieve context-aware noun predictions. In this paper, we argue that these limitations stem from the model’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.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: This work significantly contributes to multimedia/multimodal processing by bridging the gap between natural language descriptions and visual scenes in grounded situation recognition tasks. By leveraging advanced techniques in natural language understanding and computer vision, our approach enables the automatic interpretation of textual descriptions to identify and understand real-world situations depicted in multimedia content. This facilitates a deeper understanding of the context and semantics of multimedia data, leading to enhanced capabilities in content analysis, retrieval, recommendation, and generation. Furthermore, our method provides valuable insights into the integration of language and vision modalities, paving the way for more effective and intelligent multimedia systems and applications.

Submission Number: 2292