Related papers: FEAT: Full-Dimensional Efficient Attention Transfo…

Long-context transformers face significant efficiency challenges due to the quadratic cost of self-attention. However, many modern applications-from multi-turn dialogue to high-resolution vision-require contexts spanning tens of thousands…

Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a novel framework that enhances MLA inference for the…

Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…

Referring Video Object Segmentation (RVOS) requires segmenting the object in video referred by a natural language query. Existing methods mainly rely on sophisticated pipelines to tackle such cross-modal task, and do not explicitly model…

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present…

We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the…

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…

Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel representation that enables such reasoning for…

We explore on various attention methods on frequency and channel dimensions for sound event detection (SED) in order to enhance performance with minimal increase in computational cost while leveraging domain knowledge to address the…

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Transformer-based methods have achieved remarkable results in image super-resolution tasks because they can capture non-local dependencies in low-quality input images. However, this feature-intensive modeling approach is computationally…

The attention-based Transformers have been increasingly applied to audio classification because of their global receptive field and ability to handle long-term dependency. However, the existing frameworks which are mainly extended from the…

Audio-visual information fusion enables a performance improvement in speech recognition performed in complex acoustic scenarios, e.g., noisy environments. It is required to explore an effective audio-visual fusion strategy for audiovisual…

Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level prediction, converting it into a sequence multi-label…

Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on…

While transformers dominate modern vision and language models, their attention mechanism remains poorly suited for in-memory computing (IMC) devices due to intensive activation-to-activation multiplications and non-local memory access,…

Sound event localization and detection (SELD) is a task for the classification of sound events and the identification of direction of arrival (DoA) utilizing multichannel acoustic signals. For effective classification and localization, a…

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Attentive video modeling is essential for action recognition in unconstrained videos due to their rich yet redundant information over space and time. However, introducing attention in a deep neural network for action recognition is…

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…