Related papers: LiteVoxel: Low-memory Intelligent Thresholding for…

The performance of Transformer models has been enhanced by increasing the number of parameters and the length of the processed text. Consequently, fine-tuning the entire model becomes a memory-intensive process. High-performance methods for…

The audio-visual speech fusion strategy AV Align has shown significant performance improvements in audio-visual speech recognition (AVSR) on the challenging LRS2 dataset. Performance improvements range between 7% and 30% depending on the…

Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…

Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally…

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…

This paper introduces the Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset. Inspired by the…

Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge…

Dynamic head pruning in Vision Transformers (ViTs) improves efficiency by removing redundant attention heads, but existing pruning policies are often difficult to interpret and control. In this work, we propose a novel framework by…

Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of…

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…

This paper introduces a framework for super-resolution of scalable video based on compressive sensing and sparse representation of residual frames in reconnaissance and surveillance applications. We exploit efficient compressive sampling…

Deep learning-based speech enhancement (SE) methods often face significant computational challenges when needing to meet low-latency requirements because of the increased number of frames to be processed. This paper introduces the SlowFast…

In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are often too computationally intensive for vehicular applications, we propose…

Reconstructing neural radiance fields with explicit volumetric representations, demonstrated by Plenoxels, has shown remarkable advantages on training and rendering efficiency, while grid-based representations typically induce considerable…

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…

Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank…

Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of reconstruction quality and real-time performance, mainly due…

Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However, its extra parameter perturbation step doubles the…

While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited…

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…