Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- John Emil JohnsonSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works72 from public data
- Planning-oriented Autonomous Driving1,690
This work introduces Unified Autonomous Driving (UniAD), a comprehensive framework up-to-date that incorporates full-stack driving tasks in one network and is exquisitely devised to leverage advantages of each module, and provide complementary feature abstractions for agent interaction from a global perspective.
- BSN: Boundary Sensitive Network for Temporal Action Proposal Generation808
An effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts "local to global" fashion and significantly improves the state-of-the-art temporal action detection performance.
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation749
This work proposes an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously, and can achieve state-of-the-art temporal action detection performance.
- AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer456
A novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis is proposed, which achieves state-of-the-art arbitrary image/video style transfer.
- The Refined Crystal Structure of Cowpea Mosaic Virus at 2.8 Å Resolution262
The CPMV capsid was permeable to cesium ions, leading to a disturbance of the beta-annulus inside a channel-like structure, suggesting an ion channel, and the P6(1)22 crystal structure was solved by molecular replacement with the C PMV model determined in the cubic cell.
- Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion222
This work introduces a novel method, named Sparse4D, which does the iterative refinement of anchor boxes via sparsely sampling and fusing spatial-temporal features and outperforms all sparse based methods and most BEV based methods on detection task in the nuScenes dataset.
- The structure of pariacoto virus reveals a dodecahedral cage of duplex RNA.177
The 3.0 Å resolution crystal structure of Pariacoto virus reveals extensive interactions between portions of the viral RNA genome and the icosahedral capsid.
- Symphonize 3D Semantic Scene Completion with Contextual Instance Queries134
A novel paradigm termed Symphonies (Scene-from-Insts), that delves into the integration of instance queries to orchestrate 2D-to-3D reconstruction and 3D scene modeling, and fosters holistic scene comprehension by capturing context through the efficient fusion of instance queries.
- Sparse4D v2: Recurrent Temporal Fusion with Sparse Model130
An enhanced version of Sparse4D, in which the temporal fusion module is improved by implementing a recursive form of multi-frame feature sampling, which further enhances the performance of the sparse perception algorithm and achieves state-of-the-art results on the nuScenes 3D detection benchmark.
- Virus Crystals as Nanocomposite Scaffolds115
A strategy for creating systems using virus crystals as scaffolds which can be infiltrated with metal specifically palladium and platinum, providing a route for patterning these materials on the nanometer length scale is reported.
- Paint Transformer: Feed Forward Neural Painting with Stroke Prediction112
This paper formulate the task as a set prediction problem and proposes a novel Transformer-based framework, dubbed Paint Transformer, to predict the parameters of a stroke set with a feed forward network, which achieves better painting performance than previous ones with cheaper training and inference costs.
- Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer111
Inspired by the common painting process of drawing a draft and revising the details, a novel feed-forward method named Laplacian Pyramid Network (LapStyle) is introduced that can synthesize high quality stylized images in real time, where holistic style patterns are properly transferred.
- An Engineered Virus as a Scaffold for Three‐Dimensional Self‐Assembly on the Nanoscale109
Using cowpea mosaic virus, modified to express cysteine residues on the capsid exterior, gold nanoparticles were attached to the viral scaffold to produce specific interparticle distances, resulting in a 3D spherical conductive network.
- Sparse4D v3: Advancing End-to-End 3D Detection and Tracking95
This paper introduces two auxiliary training tasks (Temporal Instance Denoising and Quality Estimation) and proposes decoupled attention to make structural improvements, leading to significant enhancements in detection performance.
- MVFNet: Multi-View Fusion Network for Efficient Video Recognition94
A novel multi-view fusion (MVF) module is introduced to exploit video dynamics using separable convolution for efficiency and the proposed MVFNet can achieve state-of-the-art performance with 2D CNN's complexity.
- Learning Semantic Person Image Generation by Region-Adaptive Normalization88
This work proposes a new two-stage framework to handle the pose and appearance translation and suggests a new person image generation method by incorporating the region-adaptive normalization, in which it takes the per-region styles to guide the target appearance generation.
- 3D Domain Swapping Modulates the Stability of Members of an Icosahedral Virus Group85
Biochemical analysis supports the notion that 3D domain swapping increases the stability of RYMV, and Comparative analysis suggests that this molecular switch can also modulate the Stability of the viral capsids.
- Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation82
Experimental results demonstrate that FoI surpasses existing methods in both quantitative and qualitative evaluations, especially excelling in multi-instruction editing task.
- Discriminative representation combinations for accurate face spoofing detection77
Three discriminative representations for face presentation attack detection are introduced and a simple score fusion strategy to combine face structure cues (TFBD) with local micro-texture features (SPMT) is used.
- Influence of three-dimensional structure on the immunogenicity of a peptide expressed on the surface of a plant virus75
It is demonstrated that the mode of presentation of an epitope on a heterologous carrier can dramatically affect its immunological properties.
- 71
- Cowpea Mosaic Virus: From the Presentation of Antigenic Peptides to the Display of Active Biomaterials70
To make CPMV suitable for a wider spectrum of presentation, a technique was developed to allow surface coupling of a peptide which can serve as the anchoring point for a range of proteins.
- Structures of Picorna-Like Plant Viruses: Implications and Applications65
Structural studies of comoviruses and a nepovirus contribute to the understanding of icosahedral virus structures, the development of novel methods for investigating macromolecular assemblies, and the infrastructure for virus-based bio- and nanotechnology.
- H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation57
H-RDT (Human to Robotics Diffusion Transformer), a novel approach that leverages human manipulation data to enhance robot manipulation capabilities, is presented, demonstrating that H-RDT outperforms training from scratch and existing state-of-the-art methods.
- GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding57
GaussTR, a novel Gaussian-based TRansformer framework that unifies sparse 3D modeling with foundation model alignment through Gaussian representations to advance 3D spatial understanding, is introduced.
- Notice of Removal: DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation57
The key idea is to investigate and identify a space, namely delta image and text space that has well-aligned distribution between CLIP visual feature differences of two images and CLIP textual embedding differences of source and target texts.
- 50
- Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model49
A novel framework, i.e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of ma-nipulations.
- RISE: Self-Improving Robot Policy with Compositional World Model47
RISE is a scalable framework of robotic reinforcement learning via imagination that predicts multi-view future via a controllable dynamics model, and evaluates imagined outcomes with a progress value model, producing informative advantages for the policy improvement.
- Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence42
The proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process, and is able to learn up Scaling and Downscaling simultaneously and achieve bidirectional arbitrary image rescaling.
- Novel Strategy for Inhibiting Viral Entry by Use of a Cellular Receptor-Plant Virus Chimera33
This study utilized the CPMV chimera platform to create an antiviral against measles virus (MV) by displaying a peptide known to inhibit MV infection, which corresponds to a portion of the MV binding site on the human MV receptor CD46.
- 32
- Adversarial Dual-Student With Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation30
A context friendly differentiable geometric warping to conduct unsupervised data augmentation and a novel adversarial dual-student framework is proposed to improve the Mean-Teacher from the following two aspects.
- Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer29
A novel Transformer model termed as Master specifically for style transfer is devised so that it can not only work in the typical setting of arbitrary style transfer, but also adaptable to the few-shot setting, by only fine-tuning the Transformer encoder layer in the many-shot stage for one specific style.
- 29
- Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization28
This paper designs a two-stage cascaded module with proposed Online Adversarial Erasing (OAE) mechanism, where new and complementary regions are mined through feeding the erased feature maps of discovered regions back to the system.
- Structural Fingerprinting: Subgrouping of Comoviruses by Structural Studies of Red Clover Mottle Virus to 2.4-Å Resolution and Comparisons with Other Comoviruses28
By comparing the RCMV structure with that of other comoviruses, a structural fingerprint at the N terminus of the small subunit was identified which allowed subgrouping of comoviraluses into CPMV-like and BPMv-like viruses.
- 24
- HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models22
HyperLLaVA is introduced, which involves adaptive tuning of the projector and LLM parameters, in conjunction with a dynamic visual expert and language expert, respectively, derived from HyperNetworks, enabling dynamic projector and LLM modeling in two-stage training.
- DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection20
A novel feature fusion strategy, DynStaF (Dynamic-Static Fusion), which enhances the rich semantic information provided by the multi-frame (dynamic branch) with the accurate location information from the current single- frame (static branch).
- 20
- 20
- Position-Dependent Processing of Peptides Presented on the Surface of Cowpea Mosaic Virus20
Crystallography revealed significant differences between the structure of NIm-1A on CPMV compared with its native configuration, and alterations to the context of the NIm -1A graft were designed.
- 19
- Face spoofing detection by fusing binocular depth and spatial pyramid coding micro-texture features15
The results reveal that face spoofing detection with the fusion of the proposed features is of strong robustness and time efficiency, meanwhile outperforming other state-of-the-art traditional methods.
- Generating Multimodal Driving Scenes via Next-Scene Prediction14
A multimodal generation framework that incorporates four major data modalities, including a novel addition of the map modality, which effectively generates complex, realistic driving scenes over extended sequences, ensuring multimodal consistency and offering fine-grained control over scene elements.
- BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence12
A novel image-centric 3D perception model, BIP3D, which leverages expressive image features with explicit 3D position encoding to overcome the limitations of point-centric methods is introduced, and a spatial enhancer module is introduced to improve spatial understanding.
- Purification, Crystallization, and Preliminary X-ray Analysis of L-A: A dsRNA Yeast Virus12
LAV crystals diffracting to at least 4.5-A resolution were grown in a combination of polyethylene glycol 8000, ethylene glycol, and lithium chloride and the reservoir solution was replaced by a 2x concentrated reservoir solution in order for ethyleneglycol to function as a cryoprotectant even though initial crystals would not grow at sufficiently high concentrations of ethylene Glycol for cryoprotsection.
- 11
- WidthFormer: Toward Efficient Transformer-based BEV View Transformation11
A novel 3D positional encoding mechanism capable of accurately encapsulating 3D geometric information enables this model to compute high-quality BEV representations with only a single transformer decoder layer, which is also beneficial for existing sparse 3D object detectors.
- 11
- An Online Approach for Gesture Recognition Toward Real-World Applications10
Improved optical flow is introduced to remove global camera motion and get a better description of human motions, which improves gesture recognition performance significantly, and achieves satisfying recognition performance, while guaranteeing a real-time processing speed.
- Long term storage of virus templated fluorescent materials for sensing applications9
It is demonstrated that functionalized CPMV nanostructures can be stored for the long term, enabling their use in practical sensing applications.
- 8
- Weakly Supervised Temporal Action Detection with Shot-Based Temporal Pooling Network7
In order to distinguish action instances existing in the videos, a multi-stage Temporal Pooling Network (TPN) is designed for the purposes of predicting video categories and localizing class-specific action instances respectively.
- 6
- FineGrasp: Towards Robust Grasping for Delicate Objects3
This work proposes a novel grasping method, FineGrasp, which introduces improvements in three key aspects, including multiple network modifications to enhance the ability of to handle delicate regions and addresses the issue of label imbalance.
- Conceptual Design and Kinematic Analysis of the Diamobot: A Homogeneous Modular Robot3
In this paper, the Diamobot’s characteristics will be discussed, including the design features, kinematics and metamorphosis with a number of modules.
- 2
- 1
- 1
- 1
- 1
- Modeling network evolution by multi-agent reinforcement learning–
NEMARL is introduced, a multi-agent reinforcement learning framework for network evolution that models node-level decision making and coordination that reproduces key network properties, fits real-world data, and demonstrates effectiveness across multiple scenario tests.
- –
- –
- –
- –
- –
- BIO39) Application of cucumber green mottle mosaic virus vector as peptide presentation system–
This work has successfully constructed a novel Cucumber Green Mottle Mosaic Virus (CGMMV) vector, and base on this vector a chimeric CGMMV vector was built and both constructs were used to produce infectious transcript that was later used to inoculate muskmelon plants.
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. 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.