3 citations · 8 across the 10 of their papers we have counts for
11 papers
PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders
Man Jiang, Ouxiang Li, Weibao Xue +4
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, privacy violations,…
SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding
Yuan Sheng, Yanbin Hao, Chenxu Li +2
Long video understanding remains challenging due to its complex, diverse, and temporally scattered content. Although video large language models (Video-LLMs) can process videos las…
Accelerating Diffusion Transformer via Gradient-Optimized Cache
Junxiang Qiu, Lin Liu, Shuo Wang +3
Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progre…
Accelerating Diffusion Transformer via Error-Optimized Cache
Junxiang Qiu, Shuo Wang, Jinda Lu +4
Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time con…
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Xingyu Zhu, Beier Zhu, Yi Tan +3
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data…
Selective Vision-Language Subspace Projection for Few-shot CLIP
Xingyu Zhu, Beier Zhu, Yi Tan +3
Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of…
Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation
Jinda Lu, Shuo Wang, Yanbin Hao +3
Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation me…
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
Ouxiang Li, Yanbin Hao, Zhicai Wang +4
Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MI…
Hierarchical Space-Time Attention for Micro-Expression Recognition
Haihong Hao, Shuo Wang, Huixia Ben +3
Micro-expression recognition (MER) aims to recognize the short and subtle facial movements from the Micro-expression (ME) video clips, which reveal real emotions. Recent MER method…
Boosting Few-Shot Learning via Attentive Feature Regularization
Xingyu Zhu, Shuo Wang, Jinda Lu +3
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from differen…
Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective
Fangzhou Song, Bin Zhu, Yanbin Hao +1
Learning recipe and food image representation in common embedding space is non-trivial but crucial for cross-modal recipe retrieval. In this paper, we propose a new perspective for…