183 citations · 711 across the 37 of their papers we have counts for
40 papers
InstructMixup: Instruction-Guided Salient Patch Editing for Robust Data Augmentation
Khawar Islam, Arif Mahmood, Xin Jin +1
In image and video technologies, data augmentation is widely used to improve the generalization of deep visual models, and mixup-based strategies that interpolate between samples h…
-FracMix: Label-Preserving Self-Saliency Mixup Augmentation
Khawar Islam, Arif Mahmood, Xin Jin +1
Data augmentation is known to improve generalization of deep visual models. Recent methods favor mixup strategies that generate interpolated samples to improve model performance. H…
Structure-preserving Feature Alignment for Old Photo Colorization
Yingxue Pang, Xin Jin, Jun Fu +1
Deep learning techniques have made significant advancements in reference-based colorization by training on large-scale datasets. However, directly applying these methods to the tas…
Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts
Ruoyu Feng, Jinming Liu, Xin Jin +3
Image coding for machines (ICM) aims to compress images to support downstream AI analysis instead of human perception. For ICM, developing a unified codec to reduce information red…
Semantically Structured Image Compression via Irregular Group-Based Decoupling
Ruoyu Feng, Yixin Gao, Xin Jin +2
Image compression techniques typically focus on compressing rectangular images for human consumption, however, resulting in transmitting redundant content for downstream applicatio…
Inpaint Anything: Segment Anything Meets Image Inpainting
Tao Yu, Runseng Feng, Ruoyu Feng +4
Modern image inpainting systems, despite the significant progress, often struggle with mask selection and holes filling. Based on Segment-Anything Model (SAM), we make the first at…
Stable Attribute Group Editing for Reliable Few-shot Image Generation
Guanqi Ding, Xinzhe Han, Shuhui Wang +3
Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully…
Task Residual for Tuning Vision-Language Models
Tao Yu, Zhihe Lu, Xin Jin +2
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the well-learned kn…
Image Coding for Machines with Omnipotent Feature Learning
Ruoyu Feng, Xin Jin, Zongyu Guo +6
Image Coding for Machines (ICM) aims to compress images for AI tasks analysis rather than meeting human perception. Learning a kind of feature that is both general (for AI tasks) a…
Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks
Xin Jin, Ruoyu Feng, Simeng Sun +3
Traditional media coding schemes typically encode image/video into a semantic-unknown binary stream, which fails to directly support downstream intelligent tasks at the bitstream l…
The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
Paul Bergmann, Xin Jin, David Sattlegger +1
We introduce the first comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It is inspired by real-world visual inspection scenarios in which a…
Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression
Zongyu Guo, Runsen Feng, Zhizheng Zhang +2
Neural video codecs have demonstrated great potential in video transmission and storage applications. Existing neural hybrid video coding approaches rely on optical flow or Gaussia…
Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
Zizheng Yang, Xin Jin, Kecheng Zheng +1
Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID i…
Confounder Identification-free Causal Visual Feature Learning
Xin Li, Zhizheng Zhang, Guoqiang Wei +4
Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free o…
Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Xin Jin, Tianyu He, Xu Shen +5
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering…
MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection
Gaojian Wang, Qian Jiang, Xin Jin +2
As the remarkable development of facial manipulation technologies is accompanied by severe security concerns, face forgery detection has become a recent research hotspot. Most exis…
FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
Gaojian Wang, Qian Jiang, Xin Jin +1
The internet is filled with fake face images and videos synthesized by deep generative models. These realistic DeepFakes pose a challenge to determine the authenticity of multimedi…
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
Xin Jin, Tianyu He, Kecheng Zheng +7
Cloth-Changing person re-identification (CC-ReID) aims at matching the same person across different locations over a long-duration, e.g., over days, and therefore inevitably meets…
Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation
Xin Jin, Cuiling Lan, Wenjun Zeng +1
Many unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap, where a feature extractor is trained to fool a dom…
Local Patch AutoAugment with Multi-Agent Collaboration
Shiqi Lin, Tao Yu, Ruoyu Feng +3
Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieve…
Dense Interaction Learning for Video-based Person Re-identification
Tianyu He, Xin Jin, Xu Shen +3
Video-based person re-identification (re-ID) aims at matching the same person across video clips. Efficiently exploiting multi-scale fine-grained features while building the struct…
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
Xin Li, Xin Jin, Tao Yu +4
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance…
Style Normalization and Restitution for Domain Generalization and Adaptation
Xin Jin, Cuiling Lan, Wenjun Zeng +1
For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradat…
Learned Block-based Hybrid Image Compression
Yaojun Wu, Xin Li, Zhizheng Zhang +2
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. F…