Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks168 from public data
- ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification659
This paper proposes a new traffic representation model called Encrypted Traffic Bidirectional Encoder Representations from Transformer (ET-BERT), which pre-trains deep contextualized datagram-level representation from large-scale unlabeled data and achieves state-of-the-art performance across five encrypted traffic classification tasks.
- 575
- Shallow Attention Network for Polyp Segmentation443
The Shallow Attention Network (SANet) is proposed, which design the color exchange operation to decouple the image contents and colors, and force the model to focus more on the target shape and structure, and the shallow attention module to filter out the background noise of shallow features.
- 276
- InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring214
The non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals.
- Multi-compound Transformer for Accurate Biomedical Image Segmentation187
A unified transformer network, termed Multi-Compound Transformer (MCTrans), which incorporates rich feature learning and semantic structure mining into a unified framework and performs intra- and inter-scale self-attention, rather than single-scale attention in previous works.
- CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection154
This paper proposes a Contrastive Learning and Multi-Layer Fusion (CLMLF) method for multimodal sentiment detection, which first encode text and image to obtain hidden representations, and then uses a multi-layer fusion module to align and fuse the token-level features ofText and image.
- Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds125
This work proposes the BoxCloud, an informative and robust representation, to depict an object using the point-to-box relation, and designs an efficient box-aware feature fusion module, which leverages the aforementioned BoxCloud for reliable feature matching and embedding.
- X -Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning122
This study investigates a cross-modal knowledge transfer using Transformer for 3D dense captioning through the knowledge distillation enabled by a teacher-student framework and proposes X-Trans2Cap, which outperforms previous state-of-the-art models by a large margin.
- Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning113
DaC is presented, a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations and aligns the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy loss to reduce the distribution mismatch.
- Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds108
This work introduces a motion-centric paradigm to handle 3D SOT from a new perspective and proposes a matching-free two-stage tracker M2-Track, which significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS.
- SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training91
An asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE is built, which embeds skeleton joint sequence into graph convolutional network and reconstructs the masked skeleton joints and edges based on the prior human topology knowledge.
- Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning85
This article proposes to use the medical visual language BERT (Medical-VLBERT) model to identify the abnormality on the COVID-19 scans and generate the medical report automatically based on the detected lesion regions to produce more accurate medical reports.
- 80
- RoPGen77
Experimental results show that RoPGen can significantly improve the robustness of DL-based code authorship attribution, by respectively reducing 22.8% and 41.0% of the success rate of targeted and untargeted attacks on average.
- MMTN: Multi-Modal Memory Transformer Network for Image-Report Consistent Medical Report Generation67
A Multi-modal Memory Transformer Network (MMTN) is proposed to cope with multi- modal medical data for generating image-report consistent medical reports and achieves significant effectiveness over state-of-the-art approaches on both automatic metrics and human evaluation.
- 63
- Crystal structure of steroid reductase SRD5A reveals conserved steroid reduction mechanism63
Homology-based structural models of HsSRD5A1 and -2, together with biochemical characterization, define the substrate binding pocket of SRD5As, explain the properties of disease-related mutants and provide an important framework for further understanding of the mechanism of NADPH mediated steroids 3-oxo-Δ4 reduction.
- Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis51
This paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i.e., rendered or projected 2D images of the 3D object, to boost point cloud analysis.
- Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling50
Lumina-mGPT 2.0 is presented, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond, and is confirmed as a strong, flexible foundation model for unified multimodal generation.
- Composable Text Controls in Latent Space with ODEs47
A new efficient approach for composable text operations in the compact latent space of text, based on ordinary differential equations given arbitrary plug-in operators, which manages to generate or edit high-quality text substantially improving over previous methods in terms of generation quality and efficiency.
- 46
- Benchmarking the Robustness of LiDAR Semantic Segmentation Models44
A robust LiDAR segmentation model (RLSeg) is designed which greatly boosts the robustness with simple but effective modifications and can boost future research in robust LiDAR semantic segmentation for safety-critical applications.
- 39
- 34
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.