Search papers, labs, and topics across Lattice.
This paper introduces TRCoRSurg, a novel framework for surgical video triplet recognition that effectively integrates spatial, relational, and temporal cues to enhance understanding of complex surgical scenes. By employing a multi-scale encoder for class-specific spatial priors and a Label Correlation Modeling module with multi-scale class activation map-guided relational extraction, the model captures both static and dynamic dependencies among surgical entities. The framework's performance is validated through extensive experiments, achieving state-of-the-art results with significant improvements in average precision and reductions in triplet consistency error rates on benchmark datasets.
Achieving over 36% improvement in triplet consistency error rates, TRCoRSurg redefines how we model temporal and relational dependencies in surgical video analysis.
Understanding complex surgical scenes requires recognizing multiple interdependent entities, such as instruments, actions, and targets, while maintaining their relational consistency across time. Existing surgical triplet recognition methods struggle to jointly model intra-frame label dependencies and inter-frame temporal semantics in a unified manner. To address these limitations, we propose a unified framework that integrates spatial, relational, and temporal cues for robust surgical triplet recognition. Specifically, class-specific spatial priors are first extracted through a multi-scale encoder. These priors are then refined by a Label Correlation Modeling module with multi-scale class activation map-guided relational extraction (MS-CAMRE), enabling the model to capture both static co-occurrence patterns and dynamic contextual dependencies among triplet components. Furthermore, a Bidirectional Temporal-Relational Fusion Attention (BTRFA) module harmonizes temporal and relational representations to achieve coherent temporal reasoning. We also introduce a new evaluation metric, the Triplet Consistency Error Rate (TCER), which quantitatively measures the model's ability to preserve causal and semantic consistency across triplets. Extensive experiments on the CholecT45 and ProstaTD datasets show that our method achieves state-of-the-art performance, improving AP_IVT by 5.1 percent and 7.8 percent, respectively. Moreover, according to TCER, our approach achieves relative reductions of more than 36 percent and 25 percent on the two datasets, respectively, demonstrating the effectiveness of our framework in temporal-relational co-reasoning.
