🤖 AI Summary
This work addresses the problem of task execution verification in egocentric videos given natural-language task descriptions—specifically, multi-step daily tasks involving state changes and object interactions. To this end, the authors introduce EgoTV, the first dedicated benchmark for this problem, requiring models to perform causal, temporal, and compositional cross-modal reasoning. To tackle these challenges, they propose Neural-Symbolic Grounding (NSG): a framework that integrates symbolic task-structure modeling (e.g., task decomposition graphs) with neural multimodal representations, augmented by temporally aligned multimodal fusion and rule-guided joint inference. NSG overcomes key reasoning limitations of existing vision-language models in complex task verification. Evaluated on both synthetic EgoTV and real-world CTV datasets, NSG significantly outperforms state-of-the-art methods, enabling interpretable, step-by-step task tracking and verification. All code and data are publicly released.
📝 Abstract
To enable progress towards egocentric agents capable of understanding everyday tasks specified in natural language, we propose a benchmark and a synthetic dataset called Egocentric Task Verification (EgoTV). The goal in EgoTV is to verify the execution of tasks from egocentric videos based on the natural language description of these tasks. EgoTV contains pairs of videos and their task descriptions for multi-step tasks -- these tasks contain multiple sub-task decompositions, state changes, object interactions, and sub-task ordering constraints. In addition, EgoTV also provides abstracted task descriptions that contain only partial details about ways to accomplish a task. Consequently, EgoTV requires causal, temporal, and compositional reasoning of video and language modalities, which is missing in existing datasets. We also find that existing vision-language models struggle at such all round reasoning needed for task verification in EgoTV. Inspired by the needs of EgoTV, we propose a novel Neuro-Symbolic Grounding (NSG) approach that leverages symbolic representations to capture the compositional and temporal structure of tasks. We demonstrate NSG's capability towards task tracking and verification on our EgoTV dataset and a real-world dataset derived from CrossTask (CTV). We open-source the EgoTV and CTV datasets and the NSG model for future research on egocentric assistive agents.
