Related papers: SFVInt: Simple, Fast and Generic Variable-Length I…
Successive cancellation (SC) process is an essential component of various decoding algorithms used for polar codes and their variants. Rewinding this process seems trivial if we have access to all intermediate log-likelihood ratios (LLRs)…
Scalable video coding (SVC) is extended from its predecessor advanced video coding (AVC) because of its flexible transmission to all type of gadgets. However, SVC is more flexible and scalable than AVC, but it is more complex in determining…
The design of video encoders involves the implementation of fast mode decision (FMD) algorithm to reduce computation complexity while maintaining the performance of the coding. Although H.264/scalable video coding (SVC) achieves high…
This study presents a deep learning-based approach to seismic velocity inversion problem, focusing on both noisy and noiseless training datasets of varying sizes. Our Seismic Velocity Inversion Network (SVInvNet) introduces a novel…
Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision…
We present a novel, practical approach to speed up sparse matrix-vector multiplication (SpMVM) on GPUs. The novel key idea is to apply lossless entropy coding to further compress the sparse matrix when stored in one of the commonly…
While learned video codecs have demonstrated great promise, they have yet to achieve sufficient efficiency for practical deployment. In this work, we propose several novel ideas for learned video compression which allow for improved…
Recent advancements in Vision-Language Models (VLMs) have enabled complex multimodal tasks by processing text and image data simultaneously, significantly enhancing the field of artificial intelligence. However, these models often exhibit…
Implantable Brain-machine interfaces (BMIs) are promising for motor rehabilitation and mobility augmentation, and they demand accurate and energy-efficient algorithms. In this paper, we propose a novel spiking neural network (SNN) decoder…
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.…
Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…
Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constraining them to a…
Brain imaging data are important in brain sciences yet expensive to obtain, with big volume (i.e., large p) but small sample size (i.e., small n). To tackle this problem, transfer learning is a promising direction that leverages source data…
The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally…
Semantic segmentation has been a major topic in research and industry in recent years. However, due to the computation complexity of pixel-wise prediction and backpropagation algorithm, semantic segmentation has been demanding in…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…
We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended…
Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…
SVD-based Low-rank compression reduces transformer parameters and nominal FLOPs, but these savings often translate poorly into real LLM serving speedups. We show that this gap is largely a runtime problem: factorized checkpoints fragment…
Fine-grained visual classification (FGVC) is a challenging computer vision problem, where the task is to automatically recognise objects from subordinate categories. One of its main difficulties is capturing the most discriminative…