923 citations · 1.1k across the 48 of their papers we have counts for
11 papers · 1 filter
Text-based Aerial-Ground Person Retrieval
Xinyu Zhou, Yu Wu, Jiayao Ma +3
This work introduces Text-based Aerial-Ground Person Retrieval (TAG-PR), which aims to retrieve person images from heterogeneous aerial and ground views with textual descriptions.…
Towards One-step Causal Video Generation via Adversarial Self-Distillation
Yongqi Yang, Huayang Huang, Xu Peng +5
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumul…
Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
Yanbo Xu, Yu Wu, Sungjae Park +2
We present a mechanism to steer the sampling diversity of denoising diffusion and flow matching models, allowing users to sample from a sharper or broader distribution than the tra…
IS-Diff: Improving Diffusion-Based Inpainting with Better Initial Seed
Yongzhe Lyu, Yu Wu, Yutian Lin +1
Diffusion models have shown promising results in free-form inpainting. Recent studies based on refined diffusion samplers or novel architectural designs led to realistic results an…
Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
Xiaoliu Guan, Lielin Jiang, Hanqi Chen +6
Diffusion Transformers (DiTs) have demonstrated remarkable performance in visual generation tasks. However, their low inference speed limits their deployment in low-resource applic…
Rethinking Query-based Transformer for Continual Image Segmentation
Yuchen Zhu, Cheng Shi, Dingyou Wang +5
Class-incremental/Continual image segmentation (CIS) aims to train an image segmenter in stages, where the set of available categories differs at each stage. To leverage the built-…
Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
Qiyuan Dai, Hanzhuo Huang, Yu Wu +1
Generalized Category Discovery (GCD) aims to recognize unlabeled images from known and novel classes by distinguishing novel classes from known ones, while also transferring knowle…
Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation
Feizhen Huang, Yu Wu, Yutian Lin +1
Video-to-Audio (V2A) Generation achieves significant progress and plays a crucial role in film and video post-production. However, current methods overlook the cinematic language,…
BNMusic: Blending Environmental Noises into Personalized Music
Chi Zuo, Martin B. Møller, Pablo Martínez-Nuevo +3
While being disturbed by environmental noises, the acoustic masking technique is a conventional way to reduce the annoyance in audio engineering that seeks to cover up the noises w…
Implicit Bias Injection Attacks against Text-to-Image Diffusion Models
Huayang Huang, Xiangye Jin, Jiaxu Miao +1
The proliferation of text-to-image diffusion models (T2I DMs) has led to an increased presence of AI-generated images in daily life. However, biased T2I models can generate content…
Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
Xiaoliu Guan, Yu Wu, Huayang Huang +3
Diffusion models, known for their tremendous ability to generate high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy ri…