3 citations · 3 across the 11 of their papers we have counts for
12 papers
Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
Sixun Dong, Wei Li, Andong Deng +4
Efficient long-video understanding with vision-language models (VLMs) is often framed as selecting informative frames or visual tokens at a fixed native resolution. We show that pe…
MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts
Wenqi Marshall Guo, Qingyun Qian, Shiyu Zhou +2
Vision Language Models (VLMs) are well known for hallucinating non-existent objects in images. Objects with missing parts present a unique challenge for VLMs, stemming from both re…
Position: Universal Aesthetic Alignment Narrows Artistic Expression
Wenqi Marshall Guo, Qingyun Qian, Khalad Hasan +1
Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when "anti-aesthetic" outputs are requested for artistic or cri…
MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
Sixun Dong, Juhua Hu, Mian Zhang +3
Vision-Language Models (VLMs) demonstrate impressive performance in understanding visual content with language instruction by converting visual inputs to vision tokens. However, re…
Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
Jiawei Yao, Qi Qian, Juhua Hu
Multiple clustering aims to discover various latent structures of data from different aspects. Deep multiple clustering methods have achieved remarkable performance by exploiting c…
SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing
Qi Qian, Haiyang Xu, Ming Yan +1
Diffusion models demonstrate impressive image generation performance with text guidance. Inspired by the learning process of diffusion, existing images can be edited according to t…
Text-Guided Mixup Towards Long-Tailed Image Categorization
Richard Franklin, Jiawei Yao, Deyang Zhong +2
In many real-world applications, the frequency distribution of class labels for training data can exhibit a long-tailed distribution, which challenges traditional approaches of tra…
SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning
Qi Qian, Yuanhong Xu, Juhua Hu
Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear p…
Online Zero-Shot Classification with CLIP
Qi Qian, Juhua Hu
Vision-language pre-training such as CLIP enables zero-shot transfer that can classify images according to the candidate class names. While CLIP demonstrates an impressive zero-sho…
Efficient Personalized Text-to-image Generation by Leveraging Textual Subspace
Shian Du, Xiaotian Cheng, Qi Qian +3
Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using…
Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering
Jiawei Yao, Qi Qian, Juhua Hu
Multiple clustering has gained significant attention in recent years due to its potential to reveal multiple hidden structures of data from different perspectives. The advent of de…
Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP
Qi Qian, Yuanhong Xu, Juhua Hu
Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the clas…