Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks28 from public data
- Rethinking BiSeNet For Real-time Semantic Segmentation785
A novel and efficient structure named Short-Term Dense Concatenate network (STDC network) is proposed by removing structure redundancy by gradually reducing the dimension of feature maps and use the aggregation of them for image representation, which forms the basic module of STDC network.
- SkyReels-V2: Infinite-length Film Generative Model240
This work proposes SkyReels-V2, an Infinite-length Film Generative Model that synergizes Multi-modal Large Language Model, Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework, and designs a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models.
- 52
- Multiscale blur detection by learning discriminative deep features49
This work designs a simple yet effective 6-layer CNN model, with 5 layers for feature extraction and 1 for binary classification, which can faithfully produce patch-level blur likelihood and applies this network at three coarse-to-fine scales and optimally fuse multiscale blur likelihood maps to generate better blur detection.
- 29
- On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook21
An extensive survey is developed that outlines the trustworthiness of large generative models and practical recommendations are provided that provide practical recommendations and identify promising research directions for generative AI, ultimately promoting the trustworthiness of these models and benefiting society as a whole.
- Learning multi-path CNN for mural deterioration detection21
An eight-path CNN is designed in which seven paths are utilized for basic feature extraction from lighted images, and the remaining path is responsible for cross feature fusion, which enables the method to not only identify suitable features for different lightings but also utilize these features collaboratively through cross feature fusion.
- Image Blur Classification and Unintentional Blur Removal17
A robust image blur classifier to classify images into sharp, intentional blur, and unintentional blur, which shows superior performance of image blur classification and the promising results of unintentional blur removal of the method.
- 14
- 13
- Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions12
A novel self-discovery approach to identifying a semantic direction vector in the embedding space to restrict text embedding within a safe region and can effectively reduce NSFW content and mitigate social bias generated by diffusion models compared to several state-of-the-art baselines.
- Guardian: Guarding against Gradient Leakage with Provable Defense for Federated Learning12
This paper proposes a novel yet effective defense framework named guarding against gradient leakage (Guardian) that produces transformed gradients by jointly optimizing two theoretically-derived metrics associated with gradients for performance maintenance and privacy protection and designs an ingenious initialization strategy for faster generation of transformed gradients.
- Enhance Transferability of Adversarial Examples with Model Architecture12
This paper decomposes and reconstructs the existing model architecture into an effective model architecture, namely multi-track model architecture (MMA), and demonstrates that the transferability of adversarial examples based on the MMA significantly surpass other state-of-the-art model architectures by up to 40% with comparable overhead.
- 8
- 7
- 5
- Exploiting Pre-Trained Models and Low-Frequency Preference for Cost-Effective Transfer-based Attack3
This work proposes a novel frequency perspective to study the transferability of cross-model transferability and identifies two factors that impair the transferability: an unchangeable intrinsic difference term along with a controllable perturbation-related term and suggests employing pre-trained models as proxy models, which are freely available.
- 3
- 3
- Transferable Adversarial Examples with Bayesian Approach2
This paper leverages Bayesian approach to probe the transferability of adversarial examples and then studies what constitutes a transferability-promoting prior to design two concrete transferability-promoting priors and designs an adaptive dynamic weighting strategy for instances sampled from these priors.
- SGFL-Attack: A Similarity-Guidance Strategy for Hard-Label Textual Adversarial Attack Based on Feedback Learning2
SGFL-Attack is introduced, a novel approach that leverages a Similarity-Guidance strategy based on Feedback Learning for hard-label textual adversarial attack, with limited query budget, and significantly outperforms state-of-the-art baselines and defenses over multiple language models.
- SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images1
By introducing the semi-supervised learning technique into the adversarial attack, SemiAdv substantially decreases the number of queries required for generating adversarial samples and is capable of utilizing unlabeled raw data to launch an effective attack.
- LST2A: Lexical-Syntactic Targeted Adversarial Attack for Texts1
This work proposes a novel Lexical-Syntactic Targeted Adversarial Attack method tailored for the black-box settings, referred to as LST2A, and involves adversarial perturbations at different levels of granularities, i.e., word-level with word substitution operations and syntactic-level through rewriting the syntax of the examples.
- VarDefense: Variance‐Based Defense against Poison Attack1
A novel defense method VarDefense is proposed, which leverages an effective metric, i.e., variance, and purifying strategy to relieve the problem of poison attack and significantly surpasses state-of-the-art defense methods.
- –
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.