-
Chapter and Conference Paper
Unsupervised Prototype Adapter for Vision-Language Models
Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To leverage the valuable knowledge encod...
-
Chapter and Conference Paper
Boosting Adversarial Transferability Through Intermediate Feature
Deep neural networks are well known to be vulnerable to adversarial samples in the white-box setting. However, as research progressed, researchers discovered that adversarial samples can perform black-box atta...
-
Chapter and Conference Paper
Boosting the Robustness of Neural Networks with M-PGD
Neural networks have achieved state-of-the-art results in many fields. With further research, researchers have found that neural network models are vulnerable to adversarial examples which are carefully design...
-
Chapter and Conference Paper
Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation
We observe that human poses exhibit strong group-wise structural correlation and spatial coupling between keypoints due to the biological constraints of different body parts. This group-wise structural correla...
-
Chapter and Conference Paper
Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss
Existing approaches for unsupervised metric learning focus on exploring self-supervision information within the input image itself. We observe that, when analyzing images, human eyes often compare images again...
-
Chapter and Conference Paper
Facial Expression Recognition Based on Group Domain Random Frame Extraction
Modeling the dynamic variation of facial expression from a sequence of images is a key issue in facial expression recognition. However, the analysis of complete sequence temporal information requires significa...
-
Chapter and Conference Paper
Function-Guided Energy-Precision Optimization with Precision-Rate-Complexity Bivariate Models
In an intelligent wireless vision sensor network, an intra encoder is used for the energy-precision optimization with two control parameters: sampling ratio and quantization parameter, which have a direct impa...
-
Chapter and Conference Paper
OMEG: Oulu Multi-Pose Eye Gaze Dataset
Data is in a very important position for pattern recognition tasks including eye gaze estimation. In the literature, most researchers used normal face datasets, which are not specifically designed for eye gaze...
-
Chapter and Conference Paper
A Task-Driven Eye Tracking Dataset for Visual Attention Analysis
To facilitate the research in visual attention analysis, we design and establish a new task-driven eye tracking dataset of 47 subjects. Inspired by psychological findings that human visual behavior is tightly ...
-
Chapter and Conference Paper
A Method for Range Estimation Based on Image Processing
Striations image generated in target localization algorithm using a guide source (GTL algorithm) is always blurred and indistinct because of noise pollution. Range estimation can not be realized. In order to a...
-
Chapter and Conference Paper
Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor
We propose a feature, the Histogram of Oriented Normal Vectors (HONV), designed specifically to capture local geometric characteristics for object recognition with a depth sensor. Through our derivation, the nor...
-
Chapter and Conference Paper
Rate-Distortion Control with Delay Bound Constraint for Video Streaming over Multi-Hop Networks
We develop a relatively accurate and robust R-D control algorithm in the H.264/AVC to achieve the target bit rate. More specifically, we first present an efficient bandwidth resource allocation framework to ob...
-
Chapter
Query Language and Access Methods for Graph Databases
With the prevalence of graph data in a variety of domains, there is an increasing need for a language to query and manipulate graphs with heterogeneous attributes and structures. We present a graph query langu...
-
Chapter and Conference Paper
Wavelet Transform Based Gaussian Point Spread Function Estimation
Point spread function (PSF) estimation, an essential part for image restoration, has no accurate estimation algorithm at present. Based on the wavelet theory, a new Gaussian PSF accurate estimation algorithm i...
-
Chapter and Conference Paper
Synchronization in Two Uncoupled Chaotic Neurons
Using the membrane potential of a chaotic neuron as stimulation signal to synchronize two uncoupled Hindmarsh-Rose (HR) neurons under different initial conditions is discussed. Modulating the corresponding par...
-
Chapter and Conference Paper
Creating Customized Metasearch Engines on Demand Using SE-LEGO
Frequently, the documents needed by a user are available only via multiple search engines. For example, research papers about a particular subject may be found from the search engines of related digital librar...