Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks226 from public data
- WildDeepfake609
WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop and test the effectiveness of deepfake detectors against real-world deepfakes, and proposes two (eg. 2D and 3D) Attention-based Deepfake Detection Networks (ADDNets) to leverage the attention masks on real/fake faces for improved detection.
- M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection436
A Multi-modal Multi-scale TRansformer (M2TR), which operates on patches of different sizes to detect local inconsistencies in images at different spatial levels, and learns to detect forgery artifacts in the frequency domain to complement RGB information through a carefully designed cross modality fusion block.
- Deep-based Ingredient Recognition for Cooking Recipe Retrieval431
The feasibility of ingredient recognition is demonstrated and light is shed on this zero-shot problem peculiar to cooking recipe retrieval by experimenting on a large Chinese food dataset with images of highly complex dish appearance.
- Clean-Label Backdoor Attacks on Video Recognition Models335
This paper proposes the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions.
- Balanced Contrastive Learning for Long-Tailed Visual Recognition311
To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, a novel loss for balanced contrastive learning (BCL) is proposed that satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy.
- ObjectFormer for Image Manipulation Detection and Localization240
This paper proposes ObjectFormer, a method to detect and localize image manipulations that outperforms state-of-the-art tampering detection and localization methods, and uses a set of learnable object prototypes as mid-level representations to model the object-level consistencies among different regions.
- Cross-Domain Contrastive Learning for Unsupervised Domain Adaptation238
This work builds upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets, and introduces a simple yet effective framework CDCL, for domain alignment.
- 201
- 189
- Towards Transferable Adversarial Attacks on Vision Transformers175
A dual attack framework is introduced, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across different ViTs, and it is shown that skipping the gradients of attention during backpropagation can generate adversarial examples with high transferability.
- 173
- 160
- MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection152
A novel framework with better utilization of the depth information and fine-grained cross-modal interaction between LiDAR and camera is proposed, which consists of two important components and achieves state-of-the-art results on both 3D object detection and tracking tasks without using test-time-augmentation and ensemble techniques.
- Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models148
Reliable and Efficient Concept Erasure is introduced, a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning and achieves more efficient and thorough erasure with minor damage to original generation ability and demonstrates enhanced robustness against red-teaming tools.
- 147
- SVFormer: Semi-supervised Video Transformer for Action Recognition142
SVFormer is introduced, which adopts a steady pseudo-labeling framework (i.e., EMA-Teacher) to cope with unlabeled video samples, and a novel augmentation strategy, Tube Token-Mix, tailored for video data where video clips are mixed via a mask with consistent masked tokens over the temporal axis.
- Conductive Polymer-Coated Carbon Nanotubes To Construct Stretchable and Transparent Electrochemical Sensors116
This work develops a facile and versatile strategy to construct single-walled carbon nanotube (SWNTs)-based stretchable and transparent electrochemical sensors, by coating and binding each SWNT with conductive polymer, and protects the SWNTs junctions from separation during stretching.
- A Study of Multi-Task and Region-Wise Deep Learning for Food Ingredient Recognition107
An insightful analysis of three compelling issues in ingredient recognition, which involve recognition in either image-level or region level, pooling in either single or multiple image scales, and learning ineither single or multi-task manner are provided.
- Generalized Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data101
A novel Generalized Meta-learning based Feature-Disentangled Mixup network, namely GMeta-FDMixup is proposed to address Cross-Domain Few-Shot Learning (CD-FSL), and a novel feature disentanglement module is contributed to narrow the domain gap explicitly.
- Cross-modal Recipe Retrieval with Rich Food Attributes99
Insight is provided on the feasibility of predicting ingredient, cutting and cooking attributes for food recognition and recipe retrieval with a multi-task deep learning model and the merit of rich attributes when comparing to the recently proposed ingredient-only retrieval techniques are validated.
- 89
- Heuristic Black-Box Adversarial Attacks on Video Recognition Models88
A heuristic black-box adversarial attack model that generates adversarial perturbations only on the selected frames and regions is proposed that can significantly reduce the computation cost and lead to more than 28% reduction in query numbers for the untargeted attack on both datasets.
- Food Photo Recognition for Dietary Tracking: System and Experiment85
This work proposes a photo based dietary tracking system that employs deep-based image recognition algorithms to recognize food and analyze nutrition, which is beneficial for patients to manage their dietary and nutrition intake, and for the medical institutions to intervene and treat the chronic diseases.
- Visual Co-Occurrence Alignment Learning for Weakly-Supervised Video Moment Retrieval78
Through extensive experiments, it is demonstrated that the proposed visual co-occurrence alignment learning method outperforms the cross-modal alignment learning counterpart and achieves promising results for video moment retrieval.
- Enhancing the Self-Universality for Transferable Targeted Attacks73
A novel transfer-based targeted attack method that optimizes the adversarial perturbations without any extra training efforts for auxiliary networks on training data is proposed, named as Self-Universality (SU) attack.
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 2026-10-12. 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.