Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks124 from public data
- 817
- 217
- NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation209
Experiments show that the proposed NUWA-XL model not only generates high-quality long videos with both global and local coherence, but also decreases the average inference time from 7.55min to 26s (by 94.26%) at the same hardware setting when generating 1024 frames.
- Make Skeleton-based Action Recognition Model Smaller, Faster and Better205
A Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition, which can reach a super fast speed, and achieves state-of-the-art performance on experiment datasets: SHREC and JHMDB.
- Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space177
The C-BIoU tracker adds buffers to expand the matching space of detections and tracks, which mitigates the effect of irregular motions in two aspects and achieves state-of-the-art results on MOT datasets that focus on irregular motions and indistinguishable appearances.
- 168
- Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms167
This work presents a framework Combining the Invertible and Non-invertible (CIN) mechanisms that outperforms the current state-of-the-art methods of imperceptibility and robustness significantly.
- Graph Convolutional Neural Networks For Alzheimer’s Disease Classification124
This work implements and test a multi-class GCNN classifier for network-based classification of subjects on the AD spectrum into four categories: cognitively normal, early mild cognitive impairment, late mild Cognitive impairment, and AD, and demonstrates that GCNN is a competitive tool for staging and classification of Subjects on theAD spectrum.
- ReMOT: A model-agnostic refinement for multiple object tracking110
A Refining MOT Framework (ReMOT), which first splits imperfect tracklets and then merges the split tracklets with appearance features improved by self-supervised learning, is proposed, which can make significant improvements to state-of-the-art MOT results as powerful post-processing.
- PET image super-resolution using generative adversarial networks100
This paper presents a self-supervised SR technique for PET based on dual generative adversarial networks (GANs), which precludes the need for paired training data, ensuring wider applicability and adoptability and demonstrates that SSSR is promising in terms of image quality, peak signal-to-noise ratio, structural similarity index, contrast- to-noISE ratio, and an additional no-reference metric developed specifically for SR image quality assessment.
- Super-Resolution PET Imaging Using Convolutional Neural Networks84
A super-resolution (SR) imaging technique for PET based on convolutional neural networks (CNNs) is presented and high-resolution anatomical information based on magnetic resonance (MR) imaging is incorporated to facilitate the resolution recovery process.
- Noise2Void: unsupervised denoising of PET images61
It is shown that Noise2Void with pretraining and/or anatomical guidance leads to higher peak signal-to-noise ratios than traditional denoising schemes such as Gaussian filtering, anatomically guided non-local means filtering, and block-matching and 4D filtering.
- Crystal Structure, Solubility, and Pharmacokinetic Study on a Hesperetin Cocrystal with Piperine as Coformer56
The result revealed that the cocrystal improves the dissolution behavior of HES compared with that of the pure substance, and may provide an efficient oral formulation for HES.
- RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning55
This work proposes a novel neural architecture search method, RelativeNAS, which achieves state-of-the-art performances on ImageNet with top-1 error rate of 24.88%, and performs joint learning between fast learners and slow learners in a pairwise manner.
- MagicArticulate: Make Your 3D Models Articulation-Ready50
Extensive experiments demonstrate that MagicArticulate significantly outperforms existing methods across diverse object categories, achieving high-quality articulation that enables realistic animation.
- 50
- Decoding EEG by Visual-guided Deep Neural Networks46
A visual-guided EEG decoding method that contains a decoding stage and a generation stage that outperforms traditional machine learning methods and deep learning models in the EEG decoding task.
- Improvement of automated image stitching system for DR X-ray images43
A new automated image stitching method for full-spine and lower limb X-ray images that has higher accuracy and shorter average stitching time than previous methods and could tackle problems including image translation, rotation and small overlapping in image stitching.
- SoccerNet 2022 Challenges Results42
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team, and tasks (3-6) were novel, including their underlying data and annotations.
- 38
- Instance-Level Heterogeneous Domain Adaptation for Limited-Labeled Sketch-to-Photo Retrieval38
Experiments show that the proposed Instance-level Heterogeneous Domain Adaptation framework has set a new state of the art on three sketch-to-photo image retrieval benchmarks without extra annotations, which opens the door to train more effective models on limited-labeled heterogeneous image retrieval tasks.
- 33
- PET Image Deblurring and Super-Resolution With an MR-Based Joint Entropy Prior33
An image deblurring and super-resolution framework for PET using anatomical guidance provided by high-resolution magnetic resonance (MR) images is presented, relying on image-domain postprocessing of already-reconstructed PET images by means of spatially variant deconvolution stabilized by an MR-based joint entropy penalty function.
- 30
- 30
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.