Related papers: Cross-Attention is Not Always Needed: Dynamic Cros…

Sparse attention as a efficient method can significantly decrease the computation cost, but current sparse attention tend to rely on window self attention which block the global information flow. For this problem, we present Shifted Cross…

Learning discriminative representations for subtle localized details plays a significant role in Fine-grained Visual Categorization (FGVC). Compared to previous attention-based works, our work does not explicitly define or localize the part…

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually…

Foundation models for vision have transformed visual recognition with powerful pretrained representations and strong zero-shot capabilities, yet their potential for data-efficient learning remains largely untapped. Active Learning (AL) aims…

Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To bridge the gap between source and target domains, one prevailing strategy is…

Visual Question and Answering (VQA) problems are attracting increasing interest from multiple research disciplines. Solving VQA problems requires techniques from both computer vision for understanding the visual contents of a presented…

Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation. However, even state-of-the-art MM-DiT models like FLUX struggle with achieving precise alignment between text prompts and…

We propose an attention-based networks for transferring motions between arbitrary objects. Given a source image(s) and a driving video, our networks animate the subject in the source images according to the motion in the driving video. In…

With the rapid growth of multimedia data, such as image and text, it is a highly challenging problem to effectively correlate and retrieve the data of different media types. Naturally, when correlating an image with textual description,…

Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos. However, imbalanced unimodal performance often leads to suboptimal fused representations. Existing approaches typically adopt…

The reliability of safety-critical industrial systems hinges on accurate and robust fault diagnosis in rotating machinery. Conventional graph neural networks (GNNs) for machinery fault diagnosis face limitations in modeling complex dynamic…

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either…

Despite the success of Transformers, handling long contexts remains challenging due to the limited length generalization and quadratic complexity of self-attention. Thus Transformers often require post-training with a larger attention…

Many query-based approaches for 3D Multi-Object Tracking (MOT) adopt the tracking-by-attention paradigm, utilizing track queries for identity-consistent detection and object queries for identity-agnostic track spawning.…

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based…

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…

Video-to-video synthesis poses significant challenges in maintaining character consistency, smooth temporal transitions, and preserving visual quality during fast motion. While recent fully cross-frame self-attention mechanisms have…

Collaborative perception among multiple connected and autonomous vehicles can greatly enhance perceptive capabilities by allowing vehicles to exchange supplementary information via communications. Despite advances in previous approaches,…

Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention…

Convolutional neural networks (CNNs) and vision transformers (ViTs) have achieved remarkable success in various vision tasks. However, many architectures do not consider interactions between feature maps from different stages and scales,…