486 citations · 2.3k across the 55 of their papers we have counts for
34 papers · 1 filter
Clarity ChatGPT: An Interactive and Adaptive Processing System for Image Restoration and Enhancement
Yanyan Wei, Zhao Zhang, Jiahuan Ren +5
The generalization capability of existing image restoration and enhancement (IRE) methods is constrained by the limited pre-trained datasets, making it difficult to handle agnostic…
Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers
Jia Li, Yin Chen, Xuesong Zhang +6
In this paper, we present our advanced solutions to the two sub-challenges of Affective Behavior Analysis in the wild (ABAW) 2023: the Emotional Reaction Intensity (ERI) Estimation…
Adaptive Data-Free Quantization
Biao Qian, Yang Wang, Richang Hong +1
Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-pr…
Rethinking Data-Free Quantization as a Zero-Sum Game
Biao Qian, Yang Wang, Richang Hong +1
Data-free quantization (DFQ) recovers the performance of quantized network (Q) without accessing the real data, but generates the fake sample via a generator (G) by learning from f…
Contrastive Video Question Answering via Video Graph Transformer
Junbin Xiao, Pan Zhou, Angela Yao +4
We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1)…
Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising
Jiahuan Ren, Zhao Zhang, Richang Hong +3
Low-light image enhancement (LLIE) aims at improving the illumination and visibility of dark images with lighting noise. To handle the real-world low-light images often with heavy…
Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in The Dark
Huan Zheng, Zhao Zhang, Jicong Fan +3
Low-light stereo image enhancement (LLSIE) is a relatively new task to enhance the quality of visually unpleasant stereo images captured in dark condition. However, current methods…
Switchable Online Knowledge Distillation
Biao Qian, Yang Wang, Hongzhi Yin +2
Online Knowledge Distillation (OKD) improves the involved models by reciprocally exploiting the difference between teacher and student. Several crucial bottlenecks over the gap bet…
Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers
Jia Li, Jiantao Nie, Dan Guo +2
Representation learning and feature disentanglement have garnered significant research interest in the field of facial expression recognition (FER). The inherent ambiguity of emoti…
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization
Yangcheng Gao, Zhao Zhang, Richang Hong +3
To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floatin…
FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring
Suiyi Zhao, Zhao Zhang, Richang Hong +3
Blind image deblurring (BID) remains a challenging and significant task. Benefiting from the strong fitting ability of deep learning, paired data-driven supervised BID method has o…
Few-shot Learning with Global Relatedness Decoupled-Distillation
Yuan Zhou, Yanrong Guo, Shijie Hao +3
Despite the success that metric learning based approaches have achieved in few-shot learning, recent works reveal the ineffectiveness of their episodic training mode. In this paper…
Few-shot Partial Multi-view Learning
Yuan Zhou, Yanrong Guo, Shijie Hao +2
It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative.…
Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning
Jianfeng Dong, Zhe Ma, Xiaofeng Mao +4
This paper strives to predict fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute…
Revisiting Local Descriptor for Improved Few-Shot Classification
Jun He, Richang Hong, Xueliang Liu +2
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts…
Deep Adversarial Inconsistent Cognitive Sampling for Multi-view Progressive Subspace Clustering
Renhao Sun
Deep multi-view clustering methods have achieved remarkable performance. However, all of them failed to consider the difficulty labels (uncertainty of ground-truth for training sam…
One-bit Supervision for Image Classification
Hengtong Hu, Lingxi Xie, Zewei Du +2
This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accu…
Memory-Augmented Relation Network for Few-Shot Learning
Jun He, Richang Hong, Xueliang Liu +3
Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision…
Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation
Shijie Hao, Yuan Zhou, Yanrong Guo +3
Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually comp…
Real-world Person Re-Identification via Degradation Invariance Learning
Yukun Huang, Zheng-Jun Zha, Xueyang Fu +2
Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e.g., low-resolution, weak illumination, blurring and adverse weather. On…
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing
Hengtong Hu, Lingxi Xie, Richang Hong +1
In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vi…
Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition
Biao Qian, Yang Wang, Zhao Zhang +3
Deep convolutional neural networks have largely benefited computer vision tasks. However, the high computational complexity limits their real-world applications. To this end, many…
Robust Subspace Discovery by Block-diagonal Adaptive Locality-constrained Representation
Zhao Zhang, Jiahuan Ren, Sheng Li +3
We propose a novel and unsupervised representation learning model, i.e., Robust Block-Diagonal Adaptive Locality-constrained Latent Representation (rBDLR). rBDLR is able to recover…
Joint Subspace Recovery and Enhanced Locality Driven Robust Flexible Discriminative Dictionary Learning
Zhao Zhang, Jiahuan Ren, Weiming Jiang +4
We propose a joint subspace recovery and enhanced locality based robust flexible label consistent dictionary learning method called Robust Flexible Discriminative Dictionary Learni…