Search Results for author:
Found 13 papers, 3 papers with code
T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model.
Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification
In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models.
A light-weight rectangular decomposition large kernel convolution network for deformable medical image registration.
The RD-LKA layer utilizes anisotropic depth-wise large kernel convolutions to capture large receptive fields with an extremely low parameter count while modeling long-range spatial relationships.
Ranked #1 on
Medical Image Registration
on IXI
FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation
Controllable text-to-image (T2I) diffusion models generate images conditioned on both text prompts and semantic inputs of other modalities like edge maps.
Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models
In this paper, we explore the feasibility of leveraging language as a naturally high-quality supervision for chest CT imaging.
Adaptive Critical Subgraph Mining for Cognitive Impairment Conversion Prediction with T1-MRI-based Brain Network
These are essential for developing high-quality feature representations that reveal critical spatial impacts of structural brain changes and its topology.
Text-to-image Editing by Image Information Removal
Using the input image as a control could mitigate these issues, but since these models are trained via reconstruction, a model can simply hide information about the original image when encoding it to perfectly reconstruct the image without learning the editing task.
Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
Besides, existing methods capture global structural context only on the whole-image-level, which weaken correlation between regions and the hierarchical distribution nature of brain connectivity. We hereby propose a novel dynamic structural brain network construction method based on T1-MRI, which can dynamically localize critical regions and constrain the hierarchical distribution among them for constructing dynamic structural brain network.
Taking a Language Detour: How International Migrants Speaking a Minority Language Seek COVID-Related Information in Their Host Countries
Our data indicated that participants often took language detours, or visits to Mandarin resources for information about the COVID outbreak in their host countries.
ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies
Designing neural architectures requires immense manual efforts.
Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e. g. 7. 9% accuracy gain over "Source only" from 73. 9% to 81. 8% on "HMDB --> UCF", and 10. 3% gain on "Kinetics --> Gameplay").
Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
However, little work has been done for game image captioning which has some unique characteristics and requirements.
Hand-tremor frequency estimation in videos
We focus on the problem of estimating human hand-tremor frequency from input RGB video data.
