Related papers: ViTMAlis: Towards Latency-Critical Mobile Video An…

Web service administrators must ensure the stability of multiple systems by promptly detecting anomalies in Key Performance Indicators (KPIs). Achieving the goal of "train once, infer across scenarios" remains a fundamental challenge for…

Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional neural networks (CNN), which have been studied and adopted…

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…

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…

The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to…

The major part of the vanilla vision transformer (ViT) is the attention block that brings the power of mimicking the global context of the input image. For better performance, ViT needs large-scale training data. To overcome this data…

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

This paper introduces ViT4LPA, an innovative Vision Transformer (ViT) based approach for Load Profile Analysis (LPA). We transform time-series load profiles into load images. This allows us to leverage the ViT architecture, originally…

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used…

As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational cost. Another branch…

Mobile Edge Caching (MEC) is a revolutionary technology for the Sixth Generation (6G) of wireless networks with the promise to significantly reduce users' latency via offering storage capacities at the edge of the network. The efficiency of…

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models…

Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…

Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key challenge is how to utilize these intermediate features given…

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are…

Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on…

The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the…

Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with high-frequency visual perception compared…