146 Result(s)
-
Chapter and Conference Paper
A GNN-Enhanced Game Bot Detection Model for MMORPGs
Game bots are automated programs that assist cheating players in obtaining huge superiority in Massively Multiplayer Online Role-Playing Games (MMORPGs), which has led to an imbalance in the gaming ecosystem a...
-
Chapter and Conference Paper
Online Continual Learning with Contrastive Vision Transformer
Online continual learning (online CL) studies the problem of learning sequential tasks from an online data stream without task boundaries, aiming to adapt to new data while alleviating catastrophic forgetting ...
-
Chapter and Conference Paper
ColorFormer: Image Colorization via Color Memory Assisted Hybrid-Attention Transformer
Automatic image colorization is a challenging task that attracts a lot of research interest. Previous methods employing deep neural networks have produced impressive results. However, these colorization images...
-
Chapter and Conference Paper
Geometry-Aware Single-Image Full-Body Human Relighting
Single-image human relighting aims to relight a target human under new lighting conditions by decomposing the input image into albedo, shape and lighting. Although plausible relighting results can be achieved,...
-
Chapter and Conference Paper
Kernel Relative-prototype Spectral Filtering for Few-Shot Learning
Few-shot learning performs classification tasks and regression tasks on scarce samples. As one of the most representative few-shot learning models, Prototypical Network represents each class as sample average,...
-
Chapter and Conference Paper
Motion and Appearance Adaptation for Cross-domain Motion Transfer
Motion transfer aims to transfer the motion of a driving video to a source image. When there are considerable differences between object in the driving video and that in the source image, traditional single do...
-
Chapter and Conference Paper
On Mitigating Hard Clusters for Face Clustering
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard cluster...
-
Chapter and Conference Paper
Motion Transformer for Unsupervised Image Animation
Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to predict motion information, s...
-
Chapter and Conference Paper
A Flow Base Bi-path Network for Cross-Scene Video Crowd Understanding in Aerial View
Drones shooting can be applied in dynamic traffic monitoring, object detecting and tracking, and other vision tasks. The variability of the shooting location adds some intractable challenges to these missions,...
-
Chapter and Conference Paper
Residual and Dense UNet for Under-Display Camera Restoration
With the rapid development of electronic products, the increasing demand for full-screen devices has become a new trend, which facilitates the investigation of Under-Display Cameras (UDC). UDC can not only bri...
-
Chapter and Conference Paper
Extracting Highlights from a Badminton Video Combine Transfer Learning with Players’ Velocity
We present a novel method for extracting highlights from a badminton video. Firstly, we classify the different views of badminton videos for video segmentation through building classification model based on tr...
-
Chapter and Conference Paper
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algori...
-
Chapter and Conference Paper
Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are...
-
Chapter and Conference Paper
UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-collected database of Under-Dis...
-
Chapter and Conference Paper
QuantNet: Learning to Quantize by Learning Within Fully Differentiable Framework
Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still domin...
-
Chapter and Conference Paper
Self-attentive Pyramid Network for Single Image De-raining
Rain Streaks in a single image can severely damage the visual quality, and thus degrade the performance of current computer vision algorithms. To remove the rain streaks effectively, plenty of CNN-based method...
-
Chapter and Conference Paper
Deep Point-Wise Prediction for Action Temporal Proposal
Detecting actions in videos is an important yet challenging task. Previous works usually utilize (a) sliding window paradigms, or (b) per-frame action scoring and grou** to enumerate the possible temporal lo...
-
Chapter and Conference Paper
Near-Duplicate Video Retrieval Through Toeplitz Kernel Partial Least Squares
The existence of huge volumes of near-duplicate videos shows a rising demand on effective near-duplicate video retrieval technique in copyright violation and search result re-ranking. In this paper, Kernel Par...
-
Chapter and Conference Paper
AutoML for DenseNet Compression
DenseNet, which connects each convolutional layer to all preceding layers, is a classic model of utilizing skip connections to improve the performance and learning efficiency of deep convolutional neural netwo...
-
Chapter and Conference Paper
Homeostasis-Based CNN-to-SNN Conversion of Inception and Residual Architectures
Event-driven mode of computation provides SNNs with potential to bridge the gap between excellent performance and computational load of deep neural networks. However, SNNs are difficult to train because of the...