Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks38 from public data
- 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.
- 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.
- 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.
- 55
- COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts54
This work introduces COCO-O(ut-of-distribution), a test dataset based on COCO with 6 types of natural distribution shifts, and leverages COCO-O to conduct experiments on more than 100 modern object detectors to investigate if their improvements are credible or just over-fitting to the COCO test set.
- 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.
- Context-Aware Robust Fine-Tuning44
Context-Aware Robust Fine-tuning (CAR-FT) makes the context-aware ability of CLIP inherited into downstream tasks, and achieves both higher in-distribution (ID) and out-of-distribution (OOD) accuracy.
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models38
S-Eval is a novel LLM-based automated Safety Evaluation framework with a newly defined comprehensive risk taxonomy that can be flexibly configured and adapted to the rapid evolution of LLMs and accompanying new safety threats, test generation methods and safety critique methods thanks to the LLM-based architecture.
- Semantic invariant cross-domain image generation with generative adversarial networks38
This work proposes a new approach that utilizes GAN to translate unpaired images between domains and remain high level semantic abstraction aligned and shows that generated samples are both visually similar with target images and semantically consistent with their source counterparts.
- 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.
- WorldMark: A Unified Benchmark Suite for Interactive Video World Models21
WorldMark characterize action dynamics through a control-systems lens, which reveals models that follow translation almost perfectly while barely responding to rotation; the model with the best perceptual and aesthetic quality ranks last in translational direction accuracy and latency; and stylized scenes cost every model global consistency while leaving action dynamics largely intact.
- Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging21
An effective FGSM-based fast adversarial training method equipped with Lipschitz regularization and Auto Weight averaging, abbreviated as FGSM-LAW is proposed, demonstrating the superiority of this method over state-of-the-art fast adversarial training methods and the advanced standard adversarial training methods.
- MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models17
This work introduces MDK12-Bench, a multi-disciplinary benchmark assessing the reasoning capabilities of MLLMs via real-world K-12 examinations, and presents a novel dynamic evaluation framework to mitigate data contamination issues by bootstrapping question forms, question types, and image styles during evaluation.
- Model Inversion Attack via Dynamic Memory Learning16
This work proposes a novel Dynamic Memory Model Inversion Attack (DMMIA) to leverage historically learned knowledge, which interacts with samples (during the training) to induce diverse generations and performs better than state-of-the-art MI attack methods.
- Adversarial Examples Detection Beyond Image Space15
This work proposes a method beyond image space by a two-stream architecture, in which the image stream focuses on the pixel artifacts and the gradient stream copes with the confidence artifacts, which outperforms the existing methods under oblivious attacks and is verified effective to defend omniscient attacks.
- 15
- 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.
- 12
- Transaudio: Towards the Transferable Adversarial Audio Attack Via Learning Contextualized Perturbations11
A novel contextualized attack with deletion, insertion, and substitution adversarial behaviors, namely TransAudio, which achieves arbitrary word-level attacks based on the proposed two-stage framework and strengthens the attack transferability.
- Multi-Robot Hunting in Dynamic Environments7
A BCSLA approach is proposed to allow mobile robots to capture an intelligent evader to improve the Hunting robots' response to environmental changes and the outflank strategy is proposed for the hunting robots to force the evaders to enter a besieging circle.
- 6
- BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression5
BiWM provides a compact, reproducible path from pretrained bidirectional video models to interactive, controllable, and efficient world models, and requires only two stages: camera/action-control fine-tuning and few-step Distribution Matching Distillation.
- 5
- VI3DRM:Towards meticulous 3D Reconstruction from Sparse Views via Photo-Realistic Novel View Synthesis3
The Visual Isotropy 3D Reconstruction Model (VI3DRM), a diffusion-based sparse views 3D reconstruction model that operates within an ID consistent and perspective-disentangled 3D latent space, is introduced, capable of generating highly realistic images that are indistinguishable from real photographs.
- 2
- 2
- 2
- 1
- S-Eval: Towards Automated Safety Evaluation with Enhancement for Large Language Models1
S-Eval is proposed, a novel LLM-based automated Safety Evaluation framework that can be flexibly configured and adapted to the rapid evolution of LLMs and accompanying new safety threats, test generation methodologies, safety critique approaches, and defense mechanisms.
- 1
- –
- A Comprehensive Toolkit for Generalized Robust Vision–
A comprehensive, user-friendly toolkit for training, evaluating, and analyzing robust vision models that targets two key dimensions of robustness: Adversarial robustness-defending against malicious worst-case perturbations (adversarial examples) and Natural robustness-maintaining performance under real-world corruptions and distribution shifts.
- EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision–
Thorough benchmarks on image classification enable EasyRobust to provide an accurate robustness evaluation on vision models, and the aim is to help for training practically-robust models and promote academic and industrial progress in closing the gap between human and machine vision.
- Two-level cascade model for tracking pedestrians using thermal infrared video information–
A two-level cascade model that tracks pedestrians in a thermal infrared video by the coarse-to-fine strategy to improve the tracking accuracy and success rate and the experimental results show the superiority of the proposed tracker over the state-of-the-art trackers.
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.