Search Results for author:
Found 12 papers, 4 papers with code
Complex Scene Image Editing by Scene Graph Comprehension
Unlike object detection methods based solely on object category, our method can accurately recognize the target object by comprehending the objects and their semantic relationships within a complex scene.
Movie Genre Classification by Language Augmentation and Shot Sampling
We evaluate our method on MovieNet and Condensed Movies datasets, achieving approximate 6-9% improvement in mean Average Precision (mAP) over the baselines.
ImageSubject: A Large-scale Dataset for Subject Detection
We present a new dataset with the goal of training models to understand the layout of the objects and the context of the image then to find the main subjects among them.
Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction
Improving the sample efficiency of reinforcement learning algorithms requires effective exploration.
Fine-Grained Control of Artistic Styles in Image Generation
The style vectors are fed to the generator and discriminator to achieve fine-grained control.
EVOQUER: Enhancing Temporal Grounding with Video-Pivoted BackQuery Generation
Given a query and an untrimmed video, the temporal grounding model predicts the target interval, and the predicted video clip is fed into a video translation task by generating a simplified version of the input query.
Transforming the Latent Space of StyleGAN for Real Face Editing
But more importantly, the proposed $W$++ space achieves superior performance in both reconstruction quality and editing quality.
Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration
In the root-relative mesh recovery task, we exploit semantic relations among joints to generate a 3D mesh from the extracted 2D cues.
Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets
Monocular depth estimation plays a crucial role in 3D recognition and understanding.
Understanding Why Neural Networks Generalize Well Through GSNR of Parameters
As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well.
Teaching Compositionality to CNNs
Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions.
A backward pass through a CNN using a generative model of its activations
Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space.
