Search papers, labs, and topics across Lattice.
This paper introduces Composed Gait Retrieval (CoGR), a novel task that enhances gait recognition by integrating natural language instructions for interactive retrieval. To support this task, the authors developed the first gait-language datasets using an automated annotation pipeline powered by large vision-language models, addressing a significant gap in existing resources. The proposed ComposeGait framework effectively mitigates identity drift during retrieval, achieving state-of-the-art results with R@1 scores of 72.38% and 83.61% on the new datasets, establishing a strong baseline for future research in this area.
Gait recognition can now leverage natural language queries, achieving unprecedented accuracy while preserving identity integrity.
Gait recognition has achieved remarkable progress, yet existing methods remain confined to rigid visual matching and often overlook the potential of natural language instructions for interactive retrieval. In this paper, we introduce Composed Gait Retrieval (CoGR), a novel task that retrieves a target gait sequence based on a reference sequence and a natural language modification query. To address the absence of existing datasets for this task, we design an automated annotation pipeline powered by large vision-language models (VLMs) to construct the first gait-language datasets: Language-Augmented CCPG and Language-Augmented CASIA-B. Building on this, we propose ComposeGait, an identity-anchored composition framework designed to prevent the identity drift that arises when generic composed retrieval follows the instruction but returns the wrong person. Its Part-aware Identity Adapter (PIA) aggregates multi-frame, part-aware identity evidence into a sample-specific ID token. We inject the ID tokens into both branches of a shared Q-Former to preserve identity, while excluding the ID-token outputs from the final retrieval embeddings. Joint identity and task-adapted composed-retrieval objectives optimize this space end to end. We evaluate ComposeGait on both benchmarks and show that it achieves the best R@1 among the compared methods, reaching 72.38% on Language-Augmented CCPG and 83.61% on Language-Augmented CASIA-B. These results establish ComposeGait as a strong baseline for CoGR. The datasets and code will be made publicly available.
