Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks336 from public data
- Heterogeneous Graph Attention Network3,463
Extensive experimental results on three real-world heterogeneous graphs not only show the superior performance of the proposed model over the state-of-the-arts, but also demonstrate its potentially good interpretability for graph analysis.
- The rise and potential of large language model based agents: a survey906
A comprehensive survey on LLM-based agents is conducted, covering their construction frameworks, application scenarios, and the exploration of societies built upon LLM-based agents.
- Uncovering social network sybils in the wild460
It is found that contrary to prior conjecture, Sybil accounts in OSNs do not form tight-knit communities, Instead, they integrate into the social graph just like normal users.
- Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey336
This work introduces the background of multi-modal pre-training by reviewing the conventional deep learning, pre- training works in natural language process, computer vision, and speech, and discusses the MM-PTMs with a focus on data, objectives, network architectures, and knowledge enhanced pre- Training.
- Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark324
A new benchmark specifically dedicated to the tracking-by-language, including a large scale dataset, strong and diverse baseline methods, and a strong baseline method based on an adaptive local-global-search scheme is proposed for future works to compare.
- Uncovering social network Sybils in the wild290
These efforts to detect, characterize, and understand Sybil account activity in the Renren Online Social Network (OSN) are described and it is shown that Sybils can effectively avoid existing community-based Sybil detectors.
- A pyroptosis nanotuner for cancer therapy287
An acid-activatable nanophotosensitizer library is reported that can be used to spatiotemporally target distinct stages of endosomal maturation, enabling tunable cellular pyroptosis.
- VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows271
This work proposes a large-scale Visible-Event benchmark (termed VisEvent) and builds a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data.
- Learn to Match: Automatic Matching Network Design for Visual Tracking256
This work introduces six novel matching operators from the perspective of feature fusion instead of explicit similarity learning, namely Concatenation, Pointwise-Addition, Pairwise-Relation, FiLM, Simple-Transformer and Transductive-Guidance, to explore more feasibility on matching operator selection.
- Social Turing Tests: Crowdsourcing Sybil Detection225
A large user study on the ability of humans to detect today's Sybil accounts is conducted, using a large corpus of ground-truth Sybils from the Facebook and Renren networks and finds that while turkers vary significantly in their effectiveness, experts consistently produce near-optimal results.
- Arbitrary-Order Proximity Preserved Network Embedding210
The eigen-decomposition reweighting theorem is theoretically proved, revealing the intrinsic relationship between proximities of different orders and proposed AROPE (arbitrary-order proximity preserved embedding), a novel network embedding method based on SVD framework.
- 181
- AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries175
The proposed Adversarial Contrastive (AdCo) model not only achieves superior performances, but also can be pre-trained more efficiently with much shorter GPU time and fewer epochs.
- Pedestrian attribute recognition: A survey163
The background of pedestrian attribute recognition (PAR), including the fundamental concepts of pedestrian attributes and corresponding challenges are introduced, and existing benchmarks, including popular datasets and evaluation criterion are introduced.
- 154
- Drug repurposing screening and mechanism analysis based on human colorectal cancer organoids146
Human CRC tumor-derived organoids are established that well represent both morphological and molecular heterogeneities of original tumors and anticancer activities of drug candidates were further validated in the established patient-derived organoids-based xenograft (PDOX) system in vivo.
- Event-based Video Reconstruction via Potential-assisted Spiking Neural Network140
This paper proposes a novel Event-based Video reconstruction framework based on a fully Spiking Neural Network (EVSNN), which utilizes Leaky-Integrate-and-Fire (LIF) neuron and Membrane Potential (MP) neuron, and finds that the spiking neurons have the potential to store useful temporal information (memory) to complete such time-dependent tasks.
- 124
- 116
- VcT: Visual Change Transformer for Remote Sensing Image Change Detection115
It is demonstrated that carefully mining the common background information provides an important cue to learn the consistent representations for the two images which thus obviously facilitates the visual change detection problem.
- Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification108
A novel Cross-scale Interactive Feature Extractor (CIFE) is introduced to extract and fuse different scale CNN features as an effective backbone module for the proposed few-shot learning method.
- Large-Scale Spatio-Temporal Person Re-Identification: Algorithms and Benchmark108
This work contributes a novel Large-scale Spatio-Temporal (LaST) person re- ID dataset, including 10,862 identities with more than 228k images, and proposes an easy-to-implement baseline that works well in such challenging re-ID settings.
- Semantic-Guided Pixel Sampling for Cloth-Changing Person Re-Identification102
A semantic-guided pixel sampling approach for the cloth-changing person re-ID task that outperforms previous methods with a large margin and adopts a loss function to constrain the learned features to keep consistent before and after changes.
- 102
- A color image encryption and hiding algorithm based on hyperchaotic system and discrete cosine transform101
Simulation analysis and security evaluation demonstrate that the proposed color image encryption and hiding algorithm has better encryption performance and higher security than several advanced image encryption algorithms.
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 2026-10-13. 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.