157 citations · 1.3k across the 97 of their papers we have counts for
82 papers · 1 filter
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Kecheng Zheng, Wei Wu, Ruili Feng +6
Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new typ…
Adaptive Frequency Filters As Efficient Global Token Mixers
Zhipeng Huang, Zhizheng Zhang, Cuiling Lan +3
Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. Ho…
Knowledge-Enhanced Hierarchical Information Correlation Learning for Multi-Modal Rumor Detection
Jiawei Liu, Jingyi Xie, Fanrui Zhang +2
The explosive growth of rumors with text and images on social media platforms has drawn great attention. Existing studies have made significant contributions to cross-modal informa…
DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
Yukun Huang, Jianan Wang, Yukai Shi +3
Text-to-image diffusion models pre-trained on billions of image-text pairs have recently enabled 3D content creation by optimizing a randomly initialized differentiable 3D represen…
DreamWaltz: Make a Scene with Complex 3D Animatable Avatars
Yukun Huang, Jianan Wang, Ailing Zeng +5
We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. While recent methods have shown encour…
Streaming Video Model
Yucheng Zhao, Chong Luo, Chuanxin Tang +3
Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recog…
Spatial-Aware Token for Weakly Supervised Object Localization
Pingyu Wu, Wei Zhai, Yang Cao +2
Weakly supervised object localization (WSOL) is a challenging task aiming to localize objects with only image-level supervision. Recent works apply visual transformer to WSOL and a…
Grounding 3D Object Affordance from 2D Interactions in Images
Yuhang Yang, Wei Zhai, Hongchen Luo +3
Grounding 3D object affordance seeks to locate objects' ''action possibilities'' regions in the 3D space, which serves as a link between perception and operation for embodied agent…
Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
Xuejing Liu, Liang Li, Shuhui Wang +4
Weakly supervised Referring Expression Grounding (REG) aims to ground a particular target in an image described by a language expression while lacking the correspondence between ta…
Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images
Naishan Zheng, Jie Huang, Qi Zhu +3
Low-light image enhancement is an inherently subjective process whose targets vary with the user's aesthetic. Motivated by this, several personalized enhancement methods have been…
Degradation-agnostic Correspondence from Resolution-asymmetric Stereo
Xihao Chen, Zhiwei Xiong, Zhen Cheng +3
In this paper, we study the problem of stereo matching from a pair of images with different resolutions, e.g., those acquired with a tele-wide camera system. Due to the difficulty…
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
Zhenhuan Liu, Liang Li, Huajie Jiang +4
In recent years, creative content generations like style transfer and neural photo editing have attracted more and more attention. Among these, cartoonization of real-world scenes…
Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment
Jiayu Xiao, Liang Li, Chaofei Wang +2
Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domai…
FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization
Kecheng Zheng, Yang Cao, Kai Zhu +2
MLP-like models built entirely upon multi-layer perceptrons have recently been revisited, exhibiting the comparable performance with transformers. It is one of most promising archi…
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Jinze Chen, Yang Wang, Yang Cao +2
Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitor…
Location-Free Camouflage Generation Network
Yangyang Li, Wei Zhai, Yang Cao +1
Camouflage is a common visual phenomenon, which refers to hiding the foreground objects into the background images, making them briefly invisible to the human eye. Previous work ha…
Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning
Kai Zhu, Wei Zhai, Yang Cao +2
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimizat…
Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification
Zhipeng Huang, Jiawei Liu, Liang Li +2
RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrar…
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
Jiawei Liu, Zhipeng Huang, Liang Li +2
Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain,…
Weakly Supervised High-Fidelity Clothing Model Generation
Ruili Feng, Cheng Ma, Chengji Shen +5
The development of online economics arouses the demand of generating images of models on product clothes, to display new clothes and promote sales. However, the expensive proprieta…
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation
Zhipeng Huang, Zhizheng Zhang, Cuiling Lan +6
Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain…
Calibrated Feature Decomposition for Generalizable Person Re-Identification
Kecheng Zheng, Jiawei Liu, Wei Wu +2
Existing disentangled-based methods for generalizable person re-identification aim at directly disentangling person representations into domain-relevant interference and identity-r…
EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching
Yaya Shi, Xu Yang, Haiyang Xu +4
Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., th…
Multi-Modulation Network for Audio-Visual Event Localization
Hao Wang, Zheng-Jun Zha, Liang Li +2
We study the problem of localizing audio-visual events that are both audible and visible in a video. Existing works focus on encoding and aligning audio and visual features at the…