Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Dongcheng HuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works84 from public data
- Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain629
A novel Spatial-Phase Shallow Learning (SPSL) method is presented, which combines spatial image and phase spectrum to capture the up-sampling artifacts of face forgery to improve the transferability and theoretically analyze the validity of utilizing the phase spectrum.
- Dual Encoding for Zero-Example Video Retrieval305
This paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own and establishes a new state-of-the-art for zero-example video retrieval.
- Towards Robust Vision Transformer263
Robust Vision Transformer (RVT) is proposed, which is a new vision transformer and has superior performance with strong robustness and generalization ability compared with previous ViTs and state-of-the-art CNNs.
- One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications202
The concept-SemiPermeable structure is injected as a Membrane (SPM) into any DM to learn targeted erasing, and mean-time the alteration and erosion phenomenon is effectively mitigated via a novel Latent Anchoring fine-tuning strategy.
- Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink195
This work shows by simply using a laser beam that DNNs are easily fooled, and proposes a novel attack method called Adversarial Laser Beam (AdvLB), which enables manipulation of laser beam’s physical parameters to perform adversarial attack.
- A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking187
A comprehensive robustness benchmark called ARES-Bench is established on the image classification task and several important findings are drawn, including that there exists an intrinsic trade-off between the adversarial and natural robustness of specific noise types for the same model architecture.
- RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition152
The recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi- scale manner, and achieves state-of-the-art results on three benchmark datasets.
- AdvDrop: Adversarial Attack to DNNs by Dropping Information137
This work proposes a novel adversarial attack, named AdvDrop, which crafts adversarial examples by dropping existing information of images, and explores the adversarial robustness of DNN models in a novel perspective by dropping imperceptible de-tails to craft adversarialExamples.
- Self-Supervised Learning for Few-Shot Image Classification134
This paper proposed to train a more generalized embedding network with self-supervised learning (SSL) which can provide robust representation for downstream tasks by learning from the data itself.
- Monocular 3D Object Detection: An Extrinsic Parameter Free Approach129
A novel method to capture camera pose to formulate the detector free from extrinsic perturbation is proposed and yields the best performance compared with the other state-of-the-arts by a large margin on both KITTI 3D and nuScenes datasets.
- 122
- Progressive Relation Learning for Group Activity Recognition103
A novel method based on deep reinforcement learning to progressively refine the low-level features and high-level relations of group activities and construct a semantic relation graph (SRG) to explicitly model the relations among persons.
- Toward Understanding and Boosting Adversarial Transferability From a Distribution Perspective89
This work proposes a novel method that crafts adversarial examples by manipulating the distribution of the image and can significantly improve the transferability of the crafted attacks and achieves state-of-the-art performance in both untargeted and targeted scenarios.
- Reading-Strategy Inspired Visual Representation Learning for Text-to-Video Retrieval84
This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos.
- 80
- Composite Adversarial Attacks61
A new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of 32 base attackers, and multi-objective NSGA-II genetic algorithm is adopted for finding the strongest attack policy with minimum complexity.
- QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval54
This paper makes the first attempt in Query-based Attack against Image Retrieval (QAIR), to completely subvert the top-k retrieval results by measuring the set similarity on theTop-K retrieval results before and after attacks and guide the gradient optimization.
- Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning49
Extensive experiments on three fashion-related datasets, i.e., FashionAI, DARN, and DeepFashion, show the effectiveness of ASEN for fine-grained fashion similarity prediction and its potential for fashion reranking.
- Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association48
A dynamic reweighting scheme to better explore the hard but valuable identities while filtering out the unlearnable identities is proposed and outperforms the previous methods in multiple settings, including voice-face matching, verification and retrieval.
- 45
- MaxMatch: Semi-Supervised Learning With Worst-Case Consistency40
This article presents a generalization bound for SSL, and derives an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants, and provides a simple but effective algorithm to solve the proposed minimax problem.
- Optimizing Two-Way Partial AUC With an End-to-End Framework33
A generic framework to construct surrogate optimization problems, which supports efficient end-to-end training with deep learning, is proposed and theoretical analyses show that the objective function of the surrogate problems will achieve an upper bound of the original problem under mild conditions.
- 33
- 30
- 30
- 29
- 26
- 26
- Self-Supervised Adversarial Training26
Experimental results show that the self- supervised representation outperforms its supervised version in respect of robustness and self-supervised adversarial training can further improve the defense ability efficiently.
- Multi-level Alignment Network for Domain Adaptive Cross-modal Retrieval25
The proposed model, MAN, consistently outperforms multiple baselines, showing a superior generalization ability for target data, and establishes a new state-of-the-art for the large-scale text-to-video retrieval on TRECVID 2017, 2018 Ad-hoc Video Search benchmark.
- Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks25
This work proposes an improved conditional layer named Bilinear Residual Layer (BRL) to learning more powerful representations for LBIE task and demonstrates that this method can generate images with higher quality when compared to previous LBIe techniques.
- Robust generative adversarial network24
It is proved that the robustness in the small neighborhood of the training sets can lead to better generalization of GANs, and it is proved that RGAN can obtain a tighter generalization upper bound than the traditional GANs under mild assumptions, ensuring a theoretical superiority of RGAN over GANs.
- The Open Brands Dataset: Unified Brand Detection and Recognition at Scale21
A novel brands benchmark called "Open Brands" is established, a network called "Brand Net" is designed to handle brand recognition and Brand Net gets state-of-art mAP on Open Brand compared with existing detection methods.
- Improved Diversity-Promoting Collaborative Metric Learning for Recommendation19
The fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective is revealed and an effective sampling alternative for the CML-based paradigm is developed.
- BiFPro: A Bidirectional Facial-data Protection Framework against DeepFake17
Experimental results demonstrate that the proposed Bidirectional Facial-data Protection Framework could generate the watermarking which is fragile to FOD and at the same time robust to FIF with an average watermark extraction success rate reaching more than 95% when defending against the four advanced DeepFake techniques.
- 15
- Semi-automatic initialization of gradient vector flow snakes15
This work proposes a specific setting method based on vector field analysis that can prevent the contours from stabilizing on false boundaries in homogeneous regions or real boundaries of other objects.
- 14
- 14
- 13
- 13
- Learning to Characterize Adversarial Subspaces13
This work proposes a novel adversarial detection method which identifies adversaries by adaptively learning reasonable metrics to characterize adversarial subspaces and proposes an innovative model called Neighbor Context Encoder (NCE) to learn from k neighbors context and infer if the detected sample is normal or adversarial.
- Optimizing Partial Area Under the Top-K Curve: Theory and Practice12
Theoretical analysis shows that AUTKC has a better discrimination ability, and its Bayes optimal score function could give a correct top-<inline-formula><tex-math notation="LaTeX">$K$</tex-Math><alternatives><mml:math><mmL:mi>k</ mml:mi></mml?:math><inline-graphic xlink:href="wang-ieq4-3199970.gif"/></alternatives
- A Visual Inductive Priors Framework for Data-Efficient Image Classification12
A novel neural network architecture: DSK-net is proposed, which is very effiective in training from small data sets and with more discriminative feature extracted from DSK-net, overfitting of network is alleviated.
- Robustness enhancement against adversarial steganography via steganalyzer outputs11
A general framework is proposed that can improve the robustness of CNN steganalyzers against adversarial steganography while keeping detecting cover and conventional stego images accurately and achieving the optimal overall performance.
- 10
- 10
- 9
- Hybrid Sequence Encoder for Text Based Video Retrieval.9
This report presents a hybrid sequential encoder which make use of the utilities of not only the multi-modal sources but also the feature extractors such as GRU, aggregated vectors, graph modeling, etc in this AVS task.
- Occluded text restoration and recognition8
Experiments show that the proposed method produces good restoration quality and effectively improves the recognition rate of the following OCR process, the algorithm is optimized based on statistical analysis model and the processing time meets the real-time responding requirement.
- 8
- Automatic seeded region growing based on gradient vector flow for color image segmentation8
Experimental results demonstrate that this novel automatic seeded region growing method based on gradient vector flow is insensitive to noises and efficient to multiple objects segmentation in color images.
- GAHE: Geometry-Aware Embedding for Hyper-Relational Knowledge Graph Representation7
GAHE adopts a multi-curvature geometry-aware approach by modeling HKGs in Euclidean space, hyperbolic space, and hyperspherical space (positive curvature) in a unified framework and introduces a module termed hyper-relational subspace learning, which allocates multiple sub-relations for each hyper-relation.
- STVMamba: precipitation nowcasting with spatiotemporal prediction model7
The Spatial-Temporal Vision Mamba (STVMamba) is proposed, a novel spatiotemporal prediction model specifically designed for precipitation nowcasting that achieves high parallel computational efficiency, operates with linear time complexity, and excels at modeling long-range dependencies, overcoming the shortcomings of previous deep learning methods.
- Hierarchical Similarity Learning for Language-Based Product Image Retrieval7
This paper focuses on the cross-modal similarity measurement, and proposes a novel Hierarchical Similarity Learning (HSL) network, which first learns multi-level representations of input data by stacked encoders, and object- granularity similarity and image-granularity similarity are computed at each level.
- To Make Yourself Invisible with Adversarial Semantic Contours6
Adversarial Semantic Contour is proposed, an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour that effectively reduces the search space of pixel selection and improves the attack by introducing more semantic bias.
- 6
- 6
- 6
- 6
- 6
- 5
- Analysis of anterior segment in primary angle closure suspect with deep learning models5
AI models for PACS screening are reliable and powerful, equivalent to experienced ophthalmologists, and the mean value of diagnostic indicators of 2 CNN algorithm was similar to experienced ophthalmologists.
- 5
- Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-label Classification4
This paper proposes a novel measure named Top-K Pairwise Ranking (TKPR), and a series of analyses show that TKPR is compatible with existing ranking-based measures and establishes an empirical surrogate risk minimization framework for TKPR.
- 4
- Unsupervised Texture Segmentation Based on Geodesic Active Regions4
An algorithm based on curve evolution for unsupervised texture segmentation based on a framework of geodesic active regions is applied based on them to get satisfied boundaries between different texture regions.
- Seeded Region Merging Based on Gradient Vector Flow for Image Segmentation3
This paper proposes a fully automatic algorithm based on gradient vector flow (GVF) field and watershed-based region merging that is efficient to multiple objects segmentation, and insensitive to noises.
- Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition2
This paper makes full use of the advantages of Transformer with long-range dependency modeling to circumvent the disadvantages of CNNs limited to local receptive field and proposes a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline.
- 2
- 1
- 1
- Towards Decision-Friendly AUC: Learning Multi-Classifier with AUCµ1
A surrogate risk optimization framework to improve model performance from the perspective of AUCµ and F1-metric, and shows that the proposed surrogate risk enjoys a generalization bound in order of O(1/√N).
- 1
- –
- –
- –
- –
- DRDF–
This work proposes a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of dual router, MWF-Layer, experts and expert fusion unit, and test 12 backbones such as Visual BERT and their corresponding DRDF instances on the multimodal dataset Hateful memes, and unimodal datasets CifAR10, CIFAR100, and TinyImagenet.
- Book inner boundary extraction with modified active shape model–
One modified active shape model (MASM) method to extract book inner boundaries in the scanned book images and one “expanding training shapes” strategy is proposed to learn one shape model with better generalization ability.
- –
- Mobile-based advertisement information retrieval from images and websites–
An mobile-based prototype system to automatically extract web ad information from images and websites that can be found from top-one and top-ten returned pages in about 51.85% and 83.33% query images respectively, illustrates the effectiveness of the proposed system.
- A New Method on Matching Correspondence Features in Image Warping–
A robust method for automatically matching features in images corresponding to the same physical point on an object captured from two arbitrary viewpoints using phase congruency and can be applied to the image warping to realize its automatism.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.