Search papers, labs, and topics across Lattice.
This paper introduces ImagineAgent, a framework that uses cognitive reasoning and generative imagination to improve Open-Vocabulary Human-Object Interaction (OV-HOI) comprehension. ImagineAgent constructs cognitive maps to model relationships between entities and actions, and uses retrieval augmentation, image cropping, and diffusion models to gather knowledge and visual evidence. Experiments on SWIG-HOI and HICO-DET show state-of-the-art performance with significantly less training data.
ImagineAgent's clever combination of cognitive maps and generative tools lets it crush previous state-of-the-art on OV-HOI tasks while needing only 20% of the training data.
Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Open-Vocabulary Human-Object Interaction (OV-HOI) are limited by cross-modal hallucinations and occlusion-induced ambiguity. To address this, we propose \textbf{ImagineAgent}, an agentic framework that harmonizes cognitive reasoning with generative imagination for robust visual understanding. Specifically, our method innovatively constructs cognitive maps that explicitly model plausible relationships between detected entities and candidate actions. Subsequently, it dynamically invokes tools including retrieval augmentation, image cropping, and diffusion models to gather domain-specific knowledge and enriched visual evidence, thereby achieving cross-modal alignment in ambiguous scenarios. Moreover, we propose a composite reward that balances prediction accuracy and tool efficiency. Evaluations on SWIG-HOI and HICO-DET datasets demonstrate our SOTA performance, requiring approximately 20\% of training data compared to existing methods, validating our robustness and efficiency.