Related papers: OperA: Attention-Regularized Transformers for Surg…
Organs-at-risk (OAR) delineation in computed tomography (CT) is an important step in Radiation Therapy (RT) planning. Recently, deep learning based methods for OAR delineation have been proposed and applied in clinical practice for separate…
We present AURA-net, a convolutional neural network (CNN) for the segmentation of phase-contrast microscopy images. AURA-net uses transfer learning to accelerate training and Attention mechanisms to help the network focus on relevant image…
Transformers have recently shown promise for medical image applications, leading to an increasing interest in developing such models for medical image registration. Recent advancements in designing registration Transformers have focused on…
While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…
Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. In this paper, we observe the temporal information is…
Vision-language-action models have gained significant attention for their ability to model multimodal sequences in embodied instruction following tasks. However, most existing models rely on causal attention, which we find suboptimal for…
There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are…
Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…
Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…
Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that…
In this paper, we propose a novel method for video moment retrieval (VMR) that achieves state of the arts (SOTA) performance on R@1 metrics and surpassing the SOTA on the high IoU metric (R@1, IoU=0.7). First, we propose to use a multi-head…
Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization cliff, severely hindering practical deployment due to poor…
Every day, countless surgeries are performed worldwide, each within the distinct settings of operating rooms (ORs) that vary not only in their setups but also in the personnel, tools, and equipment used. This inherent diversity poses a…
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing…
Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not fully use spatial-temporal context and fail to tackle this…
This work proposes a novel end-to-end convolutional neural network (CNN) architecture to automatically quantify the severity of knee osteoarthritis (OA) using X-Ray images, which incorporates trainable attention modules acting as…
Transformer-based methods have recently achieved significant success in 3D human pose estimation, owing to their strong ability to model long-range dependencies. However, relying solely on the global attention mechanism is insufficient for…
Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short temporal attention span, these models suffer from error…
To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favorable practice of using…