Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks106 from public data
- Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking413
A dual-path network with a novel bi-directional dual-constrained top-ranking loss to learn discriminative feature representations and identity loss is further incorporated to model the identity-specific information to handle large intra-class variations.
- Flexible Multi-View Representation Learning for Subspace Clustering174
This paper proposes to conduct subspace clustering based on Flexible Multi-view Representation (FMR) learning, which avoids using partial information for data reconstruction, and achieves superior clustering performance over other state-ofthe-art methods.
- Universal Weighting Metric Learning for Cross-Modal Matching110
A simple and interpretable universal weighting framework for cross-modal matching is proposed, which provides a tool to analyze the interpretability of various loss functions and introduces a new polynomial loss under the universal weighted framework.
- 103
- 65
- Relationship-Preserving Knowledge Distillation for Zero-Shot Sketch Based Image Retrieval58
RPKD firstly distill the instance-level knowledge to preserve inter-class relationships without semantic similarities that require extra effort to collect and reconcile the contrastive relationships among instances between different embedding spaces, which is complementary to instance- level relationships.
- GalleryGPT: Analyzing Paintings with Large Multimodal Models55
A superior large multimodal model for painting analysis composing, dubbed GalleryGPT, is introduced, slightly modified and fine-tuned based on LLaVA architecture leveraging the authors' collected data, demonstrating its superb ability of art analysis and generalization.
- Learning Cross-Aligned Latent Embeddings for Zero-Shot Cross-Modal Retrieval54
This paper proposes a novel method termed Learning Cross-Aligned Latent Embeddings (LCALE) as an alternative to these GAN based methods for ZS-CMR, which seeks for a shared low-dimensional latent space of input multimodal features and class-embeddings by modality-specific variational autoencoders.
- 50
- CRA-Net48
This work proposes a novel end-to-end VQA model, termed Composed Relation Attention Network (CRA-Net), which devise two question-adaptive relation attention modules that can extract not only the fine-grained and precise binary relations but also the more sophisticated trinary relations.
- The capacity and energy efficiency of wireless ad hoc networks with multi-packet reception47
This work addresses the cost incurred in increasing the transport capacity of wireless ad hoc networks over what can be attained when sources and destinations communicate over multi-hop paths and nodes can transmit or receive at most one packet at a time.
- Discovering attractive segments in the user-generated video streams46
Experimental results on real-world data demonstrate the effectiveness of the proposed framework and justify the idea of predicting the popularities of segments in a video exploiting crowd-sourced time-sync comments as a bridge to analyze videos.
- 41
- 39
- 37
- 32
- 31
- Federated Learning with Domain Shift Eraser30
A novel FL framework to improve model performance by differently erasing each client’s domain skew and enhancing their consensus is proposed, and the advantages in terms of accuracy, efficiency, and generalizability are confirmed.
- 30
- Cognitive visual anomaly detection with constrained latent representations for industrial inspection robot28
A novel cognitive VAD method for industrial inspection robot is proposed based on a convolutional generative adversarial network and a denoising auto-encoder, where the adversarial learning mechanism is adopted to establish the boundary between the normal and anomaly data.
- Surveying Translation Quality Assessment27
A call for the use of translation project specifcations in all aspects of translator training and education, including exit examinations, as well as in commercial, government and non-proft translation projects.
- 24
- 22
- Learning Optimization-based Adversarial Perturbations for Attacking Sequential Recognition Models21
Extensive experiments show that the proposed adversarial attack on the general and popular DNN structure of CNN+RNN can effective fool several state-of-the-arts including four STR models and two IC models with higher successful rate and less time consumption, comparing to three latest attack methods.
- Leveraging unpaired out-of-domain data for image captioning20
This method can utilize image and text data scraped from the internet respectively to improve the performance limited in concepts-decoder framework and can transfer the knowledge learned from web data to the standard dataset.
- 15
- 14
- TKGFrame: A Two-Phase Framework for Temporal-Aware Knowledge Graph Completion12
A novel two-phase framework called TKGFrame is proposed that achieves more accurate prediction results as compared to several state-of-the-art baselines and improves the performance of predicting missing temporal facts via solving a constrained optimization problem.
- 12
- 11
- 10
- An Intelligent Knowledge Extraction Framework for Recognizing Identification Information From Real-World ID Card Images10
This paper proposes an intelligent framework for automatically recognizing ID information from images of the ID cards by conducting marginal detection using a multi-operator algorithm and localizing the region of ID card from all the proposed candidate regions with SVM classifier.
- Ad hoc distributed mutual exclusion algorithm based on token-asking10
Performance analysis and simulation results show that the AHDME algorithm has low message complexity, small space complexity, and short response delay.
- 8
- 7
- 7
- 7
- Multi-scale Dynamic Network for Temporal Action Detection6
The proposed MDN model incorporates multiple Multi-scale Dynamic Modules (MDMs), which can generate video-specific and segment-specific convolution kernels based on video content from different scales and adaptively capture rich semantic information for the prediction.
- 6
- 5
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 2
- 2
- 2
- PTAN: Principal Token-aware Adjacent Network for Compositional Temporal Grounding2
This work proposes a novel method called Principal Token-aware Adjacent Network (PTAN), which consists of three parts: Principal Temporal Token Recomposition combining video clip-level features obtained from the transformer backbone to capture more significant local features while retaining enough contextual information.
- Scene graph generation via multi-relation classification and cross-modal attention coordinator2
This paper redesigns the framework as two branches, representation learning branch and classifier learning branch, for a more balanced scene graph generator, and proposes Cross-modal Attention Coordinator (CAC) to gather consistent features from multi- modal using dynamic attention.
- 2
- 2
- 2
- 1
- 1
- Composed Query-Based Event Retrieval in Video Corpus with Multimodal Episodic Perceptron1
This paper proposes a novel event retrieval framework termed Composed Query-Based Event Retrieval (CQBER), and proposes an initial CQBER method, termed Multimodal Episodic Perceptron (MEP), which excavates complete query semantics from both observed static visual cues and various descriptions.
- 1
- 1
- 1
- 1
- Exploring nonnegative and low-rank correlation for noise-resistant spectral clustering1
A robust spectral clustering approach, termed Non-negative Low-rank Self-reconstruction (NLS), which simultaneously explores the nonnegative low-rank properties of data correlation as well as adaptively models the structural sparsity of data noise.
- Supervised Hashing with Recurrent Scaling1
This paper presents a novel framework, named Deep Recurrent Scaling Hashing (DRSH), to solve the traditional image retrieval problem and can achieve appreciable performance on major datasets, and also have the ability to explain the meaning of hash codes based on attributes.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- 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.
- –
- –
- –
- –
- –
- –
- Exploration and practice of experimental teaching of medical morphology in higher vocational college–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-16. 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.