Related papers: Selectively Informative Description can Reduce Und…
Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to…
Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and…
Personalizing text-to-image models using a limited set of images for a specific object has been explored in subject-specific image generation. However, existing methods often face challenges in aligning with text prompts due to overfitting…
Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting datasets make it difficult to fully explore the semantic…
Text-to-image generation has recently seen remarkable success, granting users with the ability to create high-quality images through the use of text. However, contemporary methods face challenges in capturing the precise semantics conveyed…
Multimodal recommendation aims to model user and item representations comprehensively with the involvement of multimedia content for effective recommendations. Existing research has shown that it is beneficial for recommendation performance…
Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…
The goal of this paper is to embed controllable factors, i.e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of…
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…
Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Unsupervised person ReID attracts a lot of attention recently, due to it works without intensive manual annotation and thus…
Text-to-image (T2I) models exhibit a significant yet under-explored "brand bias", a tendency to generate contents featuring dominant commercial brands from generic prompts, posing ethical and legal risks. We propose CIDER, a novel,…
With the help of powerful generative models, Semantic Image Compression (SIC) has achieved impressive performance at ultra-low bitrate. However, due to coarse-grained visual-semantic alignment and inherent randomness, the reliability of SIC…
Nowadays, deep learning models have reached incredible performance in the task of image generation. Plenty of literature works address the task of face generation and editing, with human and automatic systems that struggle to distinguish…
The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing…
Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned from foundation models and discretized…
With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces.…
Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual Injection, causing identity features to contaminate…
In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e.g. intelligent image manipulation. We attempt to accomplish such synthesis: given a source…
Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextual diversity. In reality, each object or attribute within a…
The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image. While, text embedding, as the pivotal intermediary between text…