Related papers: OperA: Attention-Regularized Transformers for Surg…

Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion…

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…

Accurate surgical phase recognition is crucial for computer-assisted interventions and surgical video analysis. Annotating long surgical videos is labor-intensive, driving research toward leveraging unlabeled data for strong performance…

Attention-based Transformers have revolutionized natural language processing (NLP) and shown strong performance in computer vision (CV) tasks. However, as the input sequence varies, the computational bottlenecks in Transformer models…

Surgical phase recognition is a challenging and necessary task for the development of context-aware intelligent systems that can support medical personnel for better patient care and effective operating room management. In this paper, we…

In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame $t$ may be entirely…

Surgical scene segmentation is a fundamental task for robotic-assisted laparoscopic surgery understanding. It often contains various anatomical structures and surgical instruments, where similar local textures and fine-grained structures…

Online surgical phase recognition has drawn great attention most recently due to its potential downstream applications closely related to human life and health. Despite deep models have made significant advances in capturing the…

Anomalies in multivariate time series often arise from temporal context and cross-channel coordination rather than isolated outliers. We present Pi-Transformer (Prior-Informed Transformer), a transformer with two attention pathways:…

Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based…

Intra-operative anticipation of instrument usage is a necessary component for context-aware assistance in surgery, e.g. for instrument preparation or semi-automation of robotic tasks. However, the sparsity of instrument occurrences in long…

Transformer and its variants are fundamental neural architectures in deep learning. Recent works show that learning attention in the Fourier space can improve the long sequence learning capability of Transformers. We argue that wavelet…

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Transformer-based neural network architectures achieve state-of-the-art results in different domains, from natural language processing (NLP) to computer vision (CV). The key idea of Transformers, the attention mechanism, has already led to…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often…

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Surgical phase recognition is crucial to providing surgery understanding in smart operating rooms. Despite great progress in automatic surgical phase recognition, most existing methods are still restricted by two problems. First, these…

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…