Related papers: ASTRA: Enhancing Multi-Subject Generation with Ret…

There are many excellent solutions in image restoration.However, most methods require on training separate models to restore images with different types of degradation.Although existing all-in-one models effectively address multiple types…

Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decoder can instead retrieve directly from its own internal representations. We introduce INTRA…

State-of-the-art (SOTA) Automatic Speech Recognition (ASR) systems primarily rely on acoustic information while disregarding additional multi-modal context. However, visual information are essential in disambiguation and adaptation. While…

The expanding ecosystem of pathology foundation models has produced powerful but fragmented tile-level representations, limiting their use in clinical tasks that require unified slide-level reasoning and interpretable linkage to clinically…

This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and free-viewpoint talking portrait synthesis, given an identity embedding or reference image,…

Stance detection is an important task, supporting many downstream tasks such as discourse parsing and modeling the propagation of fake news, rumors, and science denial. In this paper, we propose a novel framework for stance detection. Our…

Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to provide a powerful inductive bias, improving both convergence…

This paper proposes a novel 3D speech-to-animation (STA) generation framework designed to address the shortcomings of existing models in producing diverse and emotionally resonant animations. Current STA models often generate animations…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Template-free animatable head avatars can achieve high visual fidelity by learning expression-dependent facial deformation directly from a subject's capture, avoiding parametric face templates and hand-designed blendshape spaces. However,…

The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of…

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize…

Developing a reliable and practical face recognition system is a long-standing goal in computer vision research. Existing literature suggests that pixel-wise face alignment is the key to achieve high-accuracy face recognition. By assuming a…

Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…

Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and…

Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus more susceptible to hidden backdoor behaviors. In such…

In this work, we explore how a strategic selection of camera movements can facilitate the task of 6D multi-object pose estimation in cluttered scenarios while respecting real-world constraints important in robotics and augmented reality…

Introducing Entity-Aspect Sentiment Triplet Extraction (EASTE), a novel Aspect-Based Sentiment Analysis (ABSA) task which extends Target-Aspect-Sentiment Detection (TASD) by separating aspect categories (e.g., food#quality) into pre-defined…

Self-supervised representation learning has gained increasing attention for strong generalization ability without relying on paired datasets. However, it has not been explored sufficiently for facial representation. Self-supervised facial…

In recent years, learning-based methods have achieved significant advancements in multi-exposure image fusion. However, two major stumbling blocks hinder the development, including pixel misalignment and inefficient inference. Reliance on…