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.
- Early detection of visual impairment in young children using a smartphone-based deep learning system73
A mobile health system, the smartphone-based Apollo Infant Sight (AIS), which identifies visually impaired children with any of 16 ophthalmic disorders by recording and analyzing their gazing behaviors and facial features under visual stimuli, has the potential to be used by healthcare professionals, parents and caregivers for identifying young children with visual impairment across a wide range of ophthalmic disorders.
- Zero-Shot Ingredient Recognition by Multi-Relational Graph Convolutional Network68
Multi-relational GCN (graph convolutional network) is introduced that integrates ingredient hierarchy, attribute as well as co-occurrence for zero-shot ingredient recognition and sheds light on zero- shot ingredients recognition.
- 67
- Fine-grained Cross-modal Alignment Network for Text-Video Retrieval65
A novel Fine-grained Cross-modal Alignment Network (FCA-Net) is proposed, which considers the interactions between visual semantic units (i.e., sub-actions/sub-events) in videos and phrases in sentences for cross- modal alignment.
- Cross-Modal Transferable Adversarial Attacks from Images to Videos64
This paper proposes a simple yet effective cross-modal attack method, named as Image To Video (I2V) attack, which generates adversarial frames by minimizing the cosine similarity between features of pretrained image models from adversarial and benign examples, then combines the generated adversarial Frames to perform black-box attacks on video recognition models.
- Group connectivity of certain graphs.64
The group connectivity number Λg(G) = min{n : G is A-connected for every Abelian group with |A| ≥ n} for complete bipartite graphs, chordal graphs, and biwheels is investigated.
- FoodLMM: A Versatile Food Assistant Using Large Multi-Modal Model63
This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities, including food recognition, ingredient recognition, recipe generation, nutrition estimation, food segmentation, and multi-round conversation, to facilitate FoodLMM in dealing with tasks beyond pure text output.
- Cross-Modal Recipe Retrieval: How to Cook this Dish?55
The model can double the retrieval performance of DeViSE, a popular cross-modality model but not considering region information during learning, and the embedded multi-modal ingredient feature sheds light on the retrieval of best-match recipes.
- Video Moment Retrieval from Text Queries via Single Frame Annotation54
This paper proposes a new paradigm called ViGA, which cuts the input video into clips and contrasts between clips and queries, and achieves better results than the state-of-the-art weakly supervised methods by a large margin, even comparable to fully supervised methods in some cases.
- VideoLT: Large-scale Long-tailed Video Recognition54
FrameStack is proposed, a simple yet effective method for long-tailed video recognition that performs sampling at the frame-level in order to balance class distributions, and the sampling ratio is dynamically determined using knowledge derived from the network during training.
- Boosting the Transferability of Video Adversarial Examples via Temporal Translation51
A temporal translation attack method, which optimizes the adversarial perturbations over a set of temporal translated video clips to boost the transferability of video adversarial examples for black-box attacks on video recognition models.
- 50
- Illumination variation-resistant video-based heart rate monitoring using LAB color space46
Experimental results show that the method proposed in this paper can effectively estimate heart rate, where the mean absolute bias is 2.59 beats/min (bpm) and the 95% confidence interval is from -7.14 bpm to 3.40 bPM.
- 45
- 45
- Video Relation Detection via Multiple Hypothesis Association42
This paper proposes a novel relation association method called Multiple Hypothesis Association (MHA), which maintains multiple possible relation hypothesis during the association process in order to tolerate and handle the inaccurate or missing problem in the former steps and generate more accurate video relations.
- Multi-modal cooking workflow construction for food recipes39
MM-ReS is built, the first large-scale dataset for cooking workflow construction, consisting of 9,850 recipes with human-labeled workflow graphs and a neural encoder-decoder model that utilizes both visual and textual information to construct the cooking workflow, which achieved over 20% performance gain over existing hand-crafted baselines.
- Mixed-dish Recognition with Contextual Relation Networks39
A novel approach called contextual relation networks (CR-Nets) is proposed that encodes the implicit and explicit contextual relations among multiple dishes using region-level features and label-level co-occurrence, respectively, inspired by the intuition that people are likely to choose dishes with common eating habits.
- Fabrication of p-type ZnSe:Sb nanowires for high-performance ultraviolet light photodetector application39
The generality of the above result suggests that the as-doped p-type ZnSe NWs will find wide application in future optoelectronics devices and the work mechanism of such a p-n junction based photodetector was elucidated.
- 38
- Screening antimicrobial peptides and probiotics using multiple deep learning and directed evolution strategies37
An AMP prediction model is developed and improved using Comparing and Optimizing Multiple DEep Learning (COMDEL) algorithms, coupled with high-throughput AMP screening method, finally reaching an accuracy of 94.8% in test and 88% in experiment verification, surpassing other state-of-the-art models.
- Locate Before Answering: Answer Guided Question Localization for Video Question Answering37
LocAns is proposed, a novel approach that integrates a question localization module and an answer prediction module into an end-to-end model and achieves state-of-the-art performance on three modern long-term VideoQA datasets, NExT-QA, ActivityNet-QA, and AGQA.
- 37
- Selenite Reduction by Proteus sp. YS02: New Insights Revealed by Comparative Transcriptomics and Antibacterial Effectiveness of the Biogenic Se0 Nanoparticles35
Selenite-resistant bacterium isolated and identified as Proteus sp.
- 34
- 32
- Two-stage Visual Cues Enhancement Network for Referring Image Segmentation31
Through the two-stage enhancement, the proposed TV-Net enjoys better performances in learning fine-grained matching behaviors between the natural language expression and image, especially when the visual information of the referent is inadequate, thus produces better segmentation results.
- Attacking Video Recognition Models with Bullet-Screen Comments30
This paper introduces a novel adversarial attack, the bullet-screen comment (BSC) attack, which attacks video recognition models with BSCs, generated with a Reinforcement Learning (RL) framework.
- TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning30
This paper proposes a novel target guided dynamic mixup (TGDM) framework that leverages the target data to guide the generation of mixed images via dynamic mix up and introduces an intermediate domain generated by mixing images in the source and the target domain.
- 30
- Intelligent cataract surgery supervision and evaluation via deep learning29
DeepSurgery represents a potential approach to provide a real-time supervision and an objective surgical evaluation system for routine CS and to improve surgical outcomes.
- Hyaluronic acid-based hydrogel microspheres with multi-responsive properties for antibacterial therapy and bone regeneration in Staphylococcus aureus-infected skull defects27
Results indicate that ABOHA@ZnO hydrogel microspheres provide a promising strategy for treating infectious bone defects by combining antimicrobial, osteogenic.
- Doubly Abductive Counterfactual Inference for Text-Based Image Editing27
A Doubly Abductive Counterfactual inference framework that can support a wide spectrum of user editing intents, including addition, removal, manipulation, replacement, style transfer, and facial change, which are extensively validated in both qualitative and quantitative evaluations.
- ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning27
To solve the data imbalance problem between the source data with sufficient examples and the auxiliary target data with limited examples, a novel Multi-Expert Domain Decompositional Network (ME-D2N) is built under the umbrella of multi-expert learning.
- 26
- MVPTR26
This paper proposes to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR), a nested structure of both modalities to introduce concepts as high-level semantics and achieves state-of-the-art results on several vision and language tasks.
- RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models23
To mitigate the conflicts arising from multi-task supervision during fine-tuning of LMMs, a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach is introduced, which utilizes a diverse array of experts to address tasks of varying complexity, thereby facilitating the coordination of trainable parameters.
- 23
- Adversarial Multi-Grained Embedding Network for Cross-Modal Text-Video Retrieval23
This work contributes AME-Net with an adversarial learning strategy for learning a better joint embedding space, and experimental results on MSR-VTT and YouCook2 datasets demonstrate that the proposed framework consistently outperforms the state-of-the-art method.
- Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image22
A vision foundation model is utilized to enable the zero-shot discovery of objects in images, which serves as the initial seeds and filtering guidance to identify novel 3D objects in 3D scenes.
- Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training22
It is argued that the universal multilingual representation learned from texts allows the cross-modal interaction learned in English to be transferable to other languages, and a framework to effectively unify cross-lingual and cross- modal pre-training is proposed.
- Biomarker Localization by Combining CNN Classifier and Generative Adversarial Network22
A novel deep neural network architecture to effectively localize potential biomarkers in medical images, when only the image-level labels are available during model training, showing state-of-the-art performance in localizing biomarkers even if biomarkers are irregularly scattered and are of various sizes in images.
- On the Importance of Spatial Relations for Few-shot Action Recognition21
It is found that the spatial misalignment between objects also occurs in videos, notably more common than the temporal inconsistency, and a novel Spatial Alignment Cross Transformer (SA-CT) which learns to re-adjust the spatial relations and incorporates the temporal information is contributed.
- GCMA: Generative Cross-Modal Transferable Adversarial Attacks from Images to Videos21
This paper investigates cross-modal transferable attacks from image domains to video domains with the generator-oriented approach, i.e., crafting adversarial perturbations for each frame of video clips with the perturbation generator trained in the ImageNet domain to attack target video models.
- Self-Supervised Learning for Semi-Supervised Temporal Language Grounding21
The results demonstrate that the proposed proposed Temporal Language Grounding can achieve competitive performance compared to fully-supervised state-of-the-art methods while only requiring a small portion of temporal annotations.
- 19
- 19
- From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios19
Two new benchmarks, namely DailyFood-172 and DailyFood-16, are presented, specifically designed to curate food images from everyday meals, to evaluate the transferability of approaches from the well-curated food image domain to the everyday-life food image domain.
- Visual Relations Augmented Cross-modal Retrieval19
A novel framework that enhanced visual representation with relations between components is introduced, and visual relations are represented by the scene graph extracted from an image, then encoded by the graph convolutional neural networks for learning visual relational features.
- Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild19
This work addresses the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need of precise annotations of the gaze angle and the head pose and proposes the PAM with an Autoencoder, which is based on Self-Supervised mirror learning where the bottleneck features are angle-invariant and which works as an extra input to the dual in-painting models.
- 18
- BiC-Net: Learning Efficient Spatio-temporal Relation for Text-Video Retrieval18
A novel cross-modal retrieval framework, Bi-Branch Complementary Network (BiC-Net), is proposed, which modifies Transformer architecture to effectively bridge text-video modalities in a complementary manner via combining local spatio-temporal relation and global temporal information.
- Generalizing Face Forgery Detection via Uncertainty Learning17
This paper extends the Transformer model in a probabilistic manner by modeling dependencies between patches as Gaussian random variables and introduces a Patch Selection Module that can efficiently and accurately identify discriminative regions with high-uncertainty information, which are further utilized for final classification.
- CSPP-IQA: a multi-scale spatial pyramid pooling-based approach for blind image quality assessment17
A blind image quality assessment method (named CSPP-IQA), which is based on multi-scale spatial pyramid pooling, is proposed and achieved better accuracy, generalization and efficiency than traditional IQA methods.
- Mix-DANN and Dynamic-Modal-Distillation for Video Domain Adaptation17
This paper proposes Mix-Domain-Adversarial Neural Network and Dynamic-Modal-Distillation (MD-DMD), a novel multi-modal adversarial learning framework for unsupervised video domain adaptation that incorporates the temporal information between source and target domains, as well as the diversity of adaptability between modalities.
- 16
- 16
- 15
- Improving the Generalizability of Infantile Cataracts Detection via Deep Learning-Based Lens Partition Strategy and Multicenter Datasets15
This study provides an effective LPS for improving the generalizability of infantile cataracts detection based on deep learning Faster R-CNN and Hough transform and has the potential to be applied to multicenter slit-lamp images.
- Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection14
A comprehensive review of the current media TD approaches is provided and the challenges and trends in this field are discussed, to discuss the challenges and trends in this field for future research.
- AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning14
A novel Adversarial Contrastive Prompt Tuning (ACPT) method is proposed to robustly fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries and a detection framework AdvQDet is introduced that can detect 7 state-of-the-art query-based attacks with >99% detection rate within 5 shots.
- Mixed Dish Recognition With Contextual Relation and Domain Alignment14
The contextual relation network is proposed that encodes the implicit and explicit contextual relations among multiple dishes from region-level features and label-level co-occurrence respectively and the domain adaption networks are introduced to align both local and global features, and eliminating domain gaps of dish features across different canteens.
- Cross-domain Cross-modal Food Transfer14
The challenge of resource scarcity in the scenario that only partial data instead of a complete view of data is accessible for model transfer is addressed, and a novel generic model equipped with various loss functions including cross-modal metric learning, recipe residual loss, semantic regularization and adversarial learning is proposed for cross-domain transfer learning.
- Automatic classification of heterogeneous slit-illumination images using an ensemble of cost-sensitive convolutional neural networks13
This study proposed and developed and implemented a website-based automatic diagnosis software for pediatric cataract grading diagnosis in ophthalmology clinics and demonstrated higher specificity and sensitivity than conventional methods on multi-source datasets.
- Person-level Action Recognition in Complex Events via TSD-TSM Networks13
This paper proposes to conduct straddling expansion and region squaring on the original bounding box of a person proposal to widen the potential space of motion and interaction and lead to a square box for ROI detection.
- 12
- Adaptive Split-Fusion Transformer12
A new hybrid named Adaptive Split-Fusion Transformer (ASF-former) that treats convolutional and attention branches differently with adaptive weights is proposed that outperforms its CNN, transformer, and hybrid counterparts in terms of accuracy.
- Adaptive Temporal Grouping for Black-box Adversarial Attacks on Videos12
The adaptive temporal grouping (ATG) method, which groups video frames by the similarity of their features extracted from the ImageNet-pretrained image model, helps any black-box attack methods to optimize the adversarial perturbations over key-frames instead of all frames, where the estimated gradient of key-frame is shared with other frames in each group.
- PIC2DISH12
An all-around cooking assistant mobile app, named Pic2Dish, is developed to help users who would like to cook a dish but neither know the name of dish nor has cooking skill, and recommends a customized recipe together with video clips to guide user on how to cook the dish.
- 11
- DelayPTC-LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Models11
A novel Passenger Travel Choice prediction framework under metro delays with the Large Language Model (DelayPTC-LLM) is proposed and the results validate the advantages of DelayPTC-LLM in terms of predictive accuracy and its potential to provide actionable insights for big traffic data.
- 11
- Relation Triplet Construction for Cross-modal Text-to-Video Retrieval11
A Multi-Granularity Matching (MGM) framework that considers both fine-grained relation triplet matching and coarse- grained global semantic matching for text-to-video retrieval is proposed, representing videos as SVO triplet tracklets.
- VIREO @ TRECVID 2014: Instance Search and Semantic Indexing11
This paper summarizes the following two tasks participated by VIREO group: instance search and semantic indexing and presents the approaches and analyze the results obtained in TRECVID 2014 benchmark evaluation.
- 11
- EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs10
EchoingPixels is a framework inspired by the coexistence and interaction of visuals and sound in real-world scenes that reduces tokens from an entire combined pool of audio-visual to-kens using only 5-20% of the original to-kens, with a 2-3x speedup and memory reduction.
- 10
- Continuous protein concentration via free-flow moving reaction boundary electrophoresis10
The theoretical results indicated that the moving reaction boundary (MRB) can be quantitatively designed in free-flow electrophoresis (FFE) system; charge-to-mass ratio (Z/M) analysis could provide guidance for protein concentration optimization; and the maximum processing capacity could be predicted.
- A Review of Nutrition, Bioactivities, and Health Benefits of Custard Apple (Annona squamosa): From Phytochemicals to Potential Application9
This review is a detailed summary of the nutritional and bioactive properties, safety evaluations, and potential applications of CA.
- Application of the Lightweight BERT Model for the Warning of Tourism Public Opinion Emergencies9
This study enhances the capability to manage sudden events and public opinion crises in the tourism industry, providing a valuable tool for more effective public opinion monitoring and early warning.
- Establishing stable and highly osteogenic hiPSC-derived MSCs for 3D-printed bone graft through microenvironment modulation by CHIR99021-treated osteocytes9
A standardised system for the scalable preparation of iMSCs with improved osteogenic potential is established by combining the precise iMSC differentiation method with the CHIR99021 (C91)-treated osteocyte osteogenic microenvironment (COOME) through the activation of canonical Wnt signalling.
- HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition9
Hierarchical and Conditional Modality Selection (HCMS) is introduced, a simple yet efficient multimodal learning framework for efficient video recognition that dynamically decides on-the-fly whether to use computationally expensive modalities on a per-input basis.
- Modeling Actual Dwell Time for Rail Transit Using Data Analytics and Support Vector Regression9
This data indicates that actual dwell time at rail transit stations is one of the most significant and useful parameters in evaluating the scheduled timetable and making any dynamic operation adjustments as well as other parameters.
- 9
- Text-Driven Video Prediction8
To investigate the capability of text in causal inference for progressive motion information, the TVP framework contains a Text Inference Module (TIM), producing step-wise embeddings to regulate motion inference for subsequent frames, and a refinement mechanism incorporating global motion semantics guarantees coherent generation.
- 8
- 8
- Few-shot Food Recognition with Pre-trained Model8
This work combines CLIP's prior knowledge with the new knowledge extracted from the few-shot training set effectively for achieving good performance, and explores an adapter-based approach to fine-tune CLIP with only a few samples.
- 8
- 8
- 8
- Seroprevalence of Lyme Disease in Asian Human Populations: A Systematic Review and Meta-Analysis7
A meta-analysis of the seroprevalence of Lyme disease in Asia reveals a high seroprevalence of LD in Asia, indicating that it has become a significant public health concern in the region.
- ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning7
ControlThinker, a novel framework that employs a "comprehend-then-generate" paradigm that effectively mitigates the semantic gap between raw text prompts and target images, resulting in improved visual quality and semantic consistency across a wide range of benchmarks.
- Unsupervised content and style learning for multimodal cross-domain image translation7
This work proposes an unsupervised content and style learning method for cross-domain image translation that utilizes self-structure attention loss to preserve content structure and color constraint loss to map the color space of the reference image to the translated image.
- Unified View Empirical Study for Large Pretrained Model on Cross-Domain Few-Shot Learning7
This study presents an exhaustive empirical assessment of the Contrastive Language–Image Pre-Training model within the CD-FSL task, and establishes a straightforward baseline model, E-base, based on the authors' empirical analysis, underscoring the importance of this investigation.
- 7
- Tumour necrosis factor inhibitor combined with intravenous immunoglobulin and heparin for treatment of recurrent spontaneous abortion: A two‐centre, retrospective, cohort study7
This real‐world study aimed to explore the efficacy and safety of TNFi combined with intravenous immunoglobin (IVIG) and heparin therapy in RSA patients.
- 7
- On Synthesis for Supervised Monaural Speech Separation in Time Domain7
Synthesis way is incorporated into the time-domain speech separation approaches to deal with above broadband noises in separated sources, which can be seamlessly used in the speech separation system by a ‘plug-and-play’ way.
- Cross-modal recipe retrieval with stacked attention model7
The model can double the retrieval performance of DeViSE, a popular cross-modality model but not considering region information during learning, and the embedded multi-modal ingredient feature sheds light on the retrieval of best-match recipes.
- 7
- Neural differentiation of fibroblasts induced by intracellular co-delivery of Ascl1, Brn2 and FoxA1 via a non-viral vector of cationic polysaccharide7
A new non-viral gene carrier based on Porphyra yezoensis polysaccharide (PYP) was developed and co-delivered pABF to 3T6 cells using Ed-PYP, proving the successful conversion of 3T 6 cells into neurons.
- Image aesthetics enhancement using composition-based saliency detection7
A novel saliency detection method is presented, which utilizes the knowledge of photographic composition as priors to improve theSaliency detection results, and an online parameter selection method is proposed when utilizing GrabCut to achieve the saliency segmentation result.
- Visual saliency detection based on photographic composition7
A novel saliency detection method is presented, which utilizes the knowledge of photographic composition as priors to improve theSaliency detection results and an online parameter selection method is proposed when utilizing GrabCut to achieve the saliency segmentation result.
- IVCR-200K: A Large-Scale Multi-turn Dialogue Benchmark for Interactive Video Corpus Retrieval6
The Interactive Video Corpus Retrieval task is introduced, a more realistic setting that enables multi-turn, conversational, and realistic interactions between the user and the retrieval system, and a comprehensive framework based on multi-modal large language models (MLLMs) is proposed to help users interact in several modes with more explainable solutions.
- 6
- Exploring the Application of Graphene Oxide-Based Nanomaterials in the Repair of Osteoporotic Fractures6
A comprehensive insight is provided into the properties of GO, preparation methods for nanocomposites, advantages of these materials, and relevant mechanisms for osteoporotic fracture applications.
- A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training6
Taking the open-domain uni-modal datasets of images and texts as input, a knowledge graph is maintained as the foundation to support knowledge discovery and model pre-training in a continuous learning framework for mutual improvement.
- 6
- Human Skin Detection via Semantic Constraint6
Different from traditional skin detection algorithms, the semantic constraint is introduced, which is based on the dependence between skin pixels and human body parts (skin pixels should be overlapped with body parts) to refine the detection.
- Feature selection with spatial path coding for multimedia analysis6
A model of spatial path coding (SPC) that uses a supervised technique to select sparse features that shows better performance in terms of classification and recognition accuracy as compared with state-of-the-art algorithms is proposed.
- A 2.4 GHz low power CMOS transceiver for LR-WPAN applications6
A 2.4 GHz low power transceiver for low-rate wireless personal area network (LR-WPAN) applications is presented and the phase-locked loop based direct phase modulated transmitter is proposed to reduce power and deliver a +3 dBm output power.
- 5
- Ingredient-enriched Recipe Generation from Cooking Videos5
A framework that introduces ingredient recognition module which uses the copy mechanism to fuse the predicted ingredient information into the generated sentence is proposed which achieves the promising performances on both YouCookII and Cooking-COIN datasets.
- Transferability Estimation Based On Principal Gradient Expectation5
Principal Gradient Expectation (PGE), a simple yet effective method for assessing transferability, is proposed and extensive experiments show that the proposed metric is superior to state-of-the-art methods on all properties.
- 5
- 4
- 4
- 4
- 4
- 4
- DietLens-Eout: Large Scale Restaurant Food Photo Recognition4
A rank-loss based convolutional neural network is proposed to optimize the image features representation of restaurant dish images and it is shown that the proposed algorithm is near ready to be deployed in real-world applications.
- 4
- Structure and Randomness of the Discrete Lambert Map4
Using functional graphs induced by the Discrete Lambert Map, this work was able to find non-random properties that could potentially be used to exploit the ElGamal DSS.
- Quantitative proteomics reveals the mechanism of L-glu-induced phenolics enrichment in wheat (Triticum aestivum L.) sprouts under NaCl stress3
The mechanism of L-Glu-induced phenolics enrichment in wheat sprouts under NaCl stress was revealed, providing a theoretical basis for the growth of wheat under adversity.
- 3
- FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network3
This work proposes an attribute-driven training method that establishes global-level and local-level tasks to learn the global face feature and fine-grained attribute features, respectively and introduces a novel ID-context decoupling framework that decouples image context generation from human ID generation, ensuring the quality of contextual content as well as facilitating the learning of ID information.
- 3
- 3
- Inheritance and Development of National Traditional Sports Culture in the Context of Big Data -- Take TikTok as an example3
There are some confusions in the process of rapid dissemination, such as the increasing commercialization of traditional ethnic sports, which often neglects the dissemination of its own cultural values, the increased entertainment of traditionalethnic sports, and the neglect of its traditional sports essence.
- 3
- A stable and convenient protein electrophoresis titration device with bubble removing system3
The developed technique and apparatus greatly improves the performance of the previous MRBT device, and provides a new route toward practical application, by providing an easy and rapid setup of electrophoretic tube and safe instrumental operation.
- Object coding on the semantic graph for scene classification3
The experimental results show that the Object Coding on semantic graph can improve the classification accuracy and is proposed to address the scene classification problem.
- 2
- Revealing the Implicit Noise-based Imprint of Generative Models2
NIRNet (Noise-based Imprint Revealing Network), a novel framework that leverages noise-based imprint for the detection task, and designs a new pipeline that pioneers the use of noise patterns, derived from a Noise-based Imprint Extractor, alongside other visual features for AI-generated image detection, significantly improving detection performance.
- 2
- 2
- Open-Vocabulary Video Relation Extraction2
This work introduces Open-vocabulary Video Relation Extraction (OVRE), a novel task that views action understanding through the lens of action-centric relation triplets, and proposes a cross-modal mapping model to generate relation triplets as a sequence.
- 2
- A Hybrid Approach for Detecting Prerequisite Relations in Multi-Modal Food Recipes2
This work proposes a simple-yet-effective two-stage framework to automatically construct the prerequisite tree for a recipe by utilizing a trained classifier to detect pairwise prerequisite relations that fuses multi-modal features as input.
- MGGR: MultiModal-Guided Gaze Redirection with Coarse-to-Fine Learning2
An innovative MultiModal-Guided Gaze Redirection~(MGGR) framework that fully exploits eye-map images and target angles to adjust a given eye appearance through a designed coarse-to-fine learning that outperforms the state-of-the-art methods in terms of image quality and redirection precision.
- 1
- 1
- 1
- 1
- 1
- EKV-VBQ: Ensuring Verifiable Boolean Queries in Encrypted Key-Value Stores1
This work proposes EKV-VBQ, a scheme designed to ensure verifiable Boolean queries over encrypted key-value data, which has integrated blockchain and homomorphic Xor operations and pseudo-random functions to create a secure and verifiable datastore, while enabling efficient encrypted Boolean queries.
- 1
- 1
- 1
- Cross-domain Food Image-to-Recipe Retrieval by Weighted Adversarial Learning1
This paper proposes two novel mechanisms for cross-domain food image-to-recipe retrieval, i.e., source data selector and weighted cross-modal adversarial learning, which aims to select source samples similar to the target data and filter out distinctive ones for training.
- 1
- Combinatorial Optimization Design of Search Tree Model Based on Hash Storage1
A scheme using the idea of combinatorial optimization algorithm, which has an important application in solving the decision problem in the tree graph model, is proposed, which improves decision-making efficiency and the state space is greatly reduced by combining the two-way detection search strategy.
- 1
- Reproducibility Companion Paper1
The Inter-intra Contrastive framework aims to extract more discriminative temporal information by extending intra-negative samples in contrastive self-supervised learning by providing some custom settings to help other researchers to use the methods easily.
- Game Analysis of Government and Enterprise in Green Supply Chain Management of Agricultural Products1
- Preparation of Magnetic Drug Loaded Nanoparticles and Its Anticancer Efficacy Against Nasopharyngeal Carcinoma Cells1
The results suggest that the magnetic drug loaded nanoparticles successfully prepared have significant inhibitory effect on HNE-1 cells in vitro, and have a good therapeutic effect on NPC.
- 1
- 1
- 1
- A low power 2.4 GHz transceiver for ZigBee applications1
This transceiver adopts low power system architecture with a low-IF receiver and a direct-conversion transmitter to reduce power consumption and consists of a new low noise amplifier, a new inverter-based variable gain complex filter, and a passive quadrature mixer for image rejection.
- 1
- –
- Efficient Test-Time Retrieval Augmented Generation–
ET2RAG is a training-free method, that first retrieves the most relevant documents and augments the LLMs to efficiently generate diverse candidate responses by managing response length, that finds that partial generation is sufficient to capture the key information necessary for consensus calculation, allowing for majority voting without the need for fully generated responses.
- [Ischemic stroke infarct segmentation model based on depthwise separable convolution for multimodal magnetic resonance imaging].–
A novel encoder-decoder architecture network based on depthwise separable convolution that effectively improves the segmentation of infarct lesions, and is expected to provide a reliable support for clinical diagnosis and treatment.
- FE-RMVSNet: a feature-enhanced 3D reconstruction network–
FE-RMVSNet demonstrates superior performance in both accuracy and completeness compared to existing methods, and effectively addresses common challenges in 3D reconstruction, such as occlusion and computational limitations, by enhancing feature extraction.
- –
- –
- –
- –
- Efficacy and Safety of Antibiotics for the Treatment of Relapsing Fever: A Systematic Review and Network Meta-analysis–
A network meta-analysis showed that tetracycline is superior to penicillin for improving the cure rate and reducing the relapse rate and that tetracycline was the most effective antibiotic for reducing Jarisch-Herxheimer reactions.
- –
- –
- –
- –
- CEA++'22–
The aim of the CEA++'22 workshop is to extend the scope to accept broader topics, especially industrial applications, and the list of papers presented in the workshop is introduced.
- –
- –
- DiGAN: Directional Generative Adversarial Network for Object Transfiguration–
A new approach called Directional Generative Adversarial Network (DiGAN) in the field of object transfiguration, designed for both intra-domain and inter-domain generations and featuring a feature loss and a segmentation loss to optimize the model.
- –
- Developmental validation of the EX16+22Y system–
The results show that the EX16+22Y system is a robust and reliable amplification kit which can be used for human identification testing and validation for the human fluorescent STR multiplex PCR reagent.
- –
- Large-scale video semantic recognition based on consistency of segment-level and video-level predictions–
This paper proposes a video semantic recognition algorithm based on the consistency of video- and segment-level predictions that achieves 82.62% mean average precision on the video segment semantic recognition task using the large-scale video dataset YouTube-8M.
- Function-Structure Collaborative Mapping Induced by Universal Triple I Systems–
The effectiveness of the proposed function-structure collaborative mapping method based on the triple I system is confirmed, and the problem of function tree modeling is effectively solved, which promotes the development of product concept design.
- VPSO-Based CCR-ELM for Imbalanced Classification–
The experimental results for nine imbalance dataset show that particle swarm optimization with variable length can find better parameters of CCR-ELM and corresponding CCR -ELM had better classification accuracy.
- Nonuniform Granularity‐Based Classification in Social Interest Detection–
The results for comparing with Naive Bayes, k-nearest neighbor, and so forth validate the better classification performance of the proposed algorithm for large scale resources.
- –
- –
- Development of machine vision system to detect meat mass of pig prior to slaughtering–
The system being cost, labor and time efficient, can be used for detection of meat mass of pig in commercial pig farming and showed that the former method to predict meat mass was better.
- –
- –
- The Main Controversy and Current Directions on Mismatch Negativity–
The studies on MMN found that it is not auditory-specific: it not only occurs in auditory modality, but also in other modalities, such as visual modality.
- –
- Comparison & analysis of channel capacity of UI and IT in MIMO wireless channel–
The simulation result indicate that performance of channel capacity with the optimal power allocation outperform the average power allocation and the capacity is asymptotically linear in the logarithm ofSNR and the minimum of the number of transmit and receive antennas with the growth of SNR.
- –
- –
- New region-of-interest image coding method–
A new method is proposed which removes the high-frequency part of BG of the Maxshift method which can improve compression ratio, reduce the computer complexity and optimize ROI coding purpose.
- –
- –
- –
- –
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.