Related papers: Minimalistic Video Saliency Prediction via Efficie…
Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…
In interventional radiology, short video sequences of vein structure in motion are captured in order to help medical personnel identify vascular issues or plan intervention. Semantic segmentation can greatly improve the usefulness of these…
We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…
While previous CNN-based models have exhibited promising results for salient object detection (SOD), their ability to explore global long-range dependencies is restricted. Our previous work, the Visual Saliency Transformer (VST), addressed…
In recent years, finding an effective and efficient strategy for exploiting spatial and temporal information has been a hot research topic in video saliency prediction (VSP). With the emergence of spatio-temporal transformers, the weakness…
Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient…
Since being introduced in 2020, Vision Transformers (ViT) has been steadily breaking the record for many vision tasks and are often described as ``all-you-need" to replace ConvNet. Despite that, ViTs are generally computational,…
Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recognition, use a video backbone to directly extract…
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal…
Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices…
The primary aim of Audio-Visual Segmentation (AVS) is to precisely identify and locate auditory elements within visual scenes by accurately predicting segmentation masks at the pixel level. Achieving this involves comprehensively…
Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource…
For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture long-range correlations. However, existing research uses…
BiSeNet has been proved to be a popular two-stream network for real-time segmentation. However, its principle of adding an extra path to encode spatial information is time-consuming, and the backbones borrowed from pretrained tasks, e.g.,…
Skin lesion segmentation (SLS) plays an important role in skin lesion analysis. Vision transformers (ViTs) are considered an auspicious solution for SLS, but they require more training data compared to convolutional neural networks (CNNs)…
Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively…
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…
As a bio-inspired vision sensor, the spike camera emulates the operational principles of the fovea, a compact retinal region, by employing spike discharges to encode the accumulation of per-pixel luminance intensity. Leveraging its high…
Video action recognition (VAR) plays crucial roles in various domains such as surveillance, healthcare, and industrial automation, making it highly significant for the society. Consequently, it has long been a research spot in the computer…