Related papers: Bridging the Skeleton-Text Modality Gap: Diffusion…

The success of Zero-shot Action Recognition (ZSAR) methods is intrinsically related to the nature of semantic side information used to transfer knowledge, although this aspect has not been primarily investigated in the literature. This work…

Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with large language models (LLMs). We present Diffusion-Link, a…

Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…

Although diffusion models have achieved remarkable progress in multi-modal magnetic resonance imaging (MRI) translation tasks, existing methods still tend to suffer from anatomical inconsistencies or degraded texture details when handling…

Low-field (LF) magnetic resonance imaging (MRI) democratizes access to diagnostic imaging but is fundamentally limited by low signal-to-noise ratio and significant tissue contrast distortion due to field-dependent relaxation dynamics.…

Tactile sensing provides a promising sensing modality for object pose estimation in manipulation settings where visual information is limited due to occlusion or environmental effects. However, efficiently leveraging tactile data for…

Recently, the diffusion model has emerged as a superior generative model that can produce high quality and realistic images. However, for medical image translation, the existing diffusion models are deficient in accurately retaining…

Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement methods for accurate text rendering. However, the critical…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive…

We introduce the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign class examples to recognize the instances of unseen signs. To this end, we propose to utilize the…

Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To bridge this gap, we…

Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…

Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…

Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settings is achieving comprehensive mode coverage, ensuring the…

Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting. However,…

Text-to-video (T2V) synthesis has gained increasing attention in the community, in which the recently emerged diffusion models (DMs) have promisingly shown stronger performance than the past approaches. While existing state-of-the-art DMs…

Few-shot action recognition (FSAR) has recently made notable progress through set matching and efficient adaptation of large-scale pre-trained models. However, two key limitations persist. First, existing set matching metrics typically rely…

Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…

In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion…