Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks16 from public data
- Depth Enhanced Saliency Detection Method368
This paper proposes a saliency detection method using the additional depth information and saliency cues are provided to follow the laws of the visually salient stimuli in both color and depth spaces.
- Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack50
This work identifies a new task that stealthily embeds attacks inside the image denoising module widely deployed in multimedia devices as an image post-processing operation to simultaneously enhance the visual image quality and fool DNNs.
- Co-Saliency Detection via Base Reconstruction39
This paper addresses the co-saliency detection to a reconstruction problem: the foreground could be well reconstructed by using the reconstruction bases, which are extracted from each image and have the similar appearances in the feature space.
- Bias Field Poses a Threat to DNN-Based X-Ray Recognition35
The adversarial-smooth bias field attack that can locally tune the bias field with joint smooth & adversarial constraints can not only fool the DNNs effectively but also retain very high level of realisticity.
- Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading33
This paper identifies and introduces a novel solution to an entirely new task, termed as adversarial exposure attack, which is able to produce natural exposure images and mislead the state-of-the-art DNNs.
- 13
- 12
- 11
- Defense for adversarial videos by self-adaptive JPEG compression and optical texture9
A new two-stage framework for defending video adversarial attack contains two main components, namely self-adaptive Joint Photographic Experts Group (JPEG) compression defense and optical texture based defense (OTD).
- 5
- 1
- Towards Calibration Enhanced Network by Inverse Adversarial Attack–
This paper introduces a novel task, termed Inverse Adversarial Attack (IAA), to highlight potential underconfidence issues in models, and incorporates examples generated by IAA during the training process to improve model calibration.
- –
- –
- –
- –
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 2026-10-11. 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. You will be asked to sign in.