![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 Challenge: Report
Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this prob...
-
Chapter and Conference Paper
Revisiting TENT for Test-Time Adaption Semantic Segmentation and Classification Head Adjustment
Test-time adaption is very effective at solving the domain shift problem where the training data and testing data are sampled from different domains. However, most test-time adaption methods made their success...
-
Chapter and Conference Paper
Enhancing Adversarial Transferability from the Perspective of Input Loss Landscape
The transferability of adversarial examples enables the black-box attacks and poses a threat to the application of deep neural networks in real-world, which has attracted great attention in recent years. Regar...
-
Chapter and Conference Paper
Affinity-Aware Relation Network for Oriented Object Detection in Aerial Images
Object detection in aerial images is a challenging task due to the oriented and densely packed objects. However, densely packed objects constitute a significant characteristic of aerial images: objects are not...
-
Chapter and Conference Paper
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information acr...
-
Chapter and Conference Paper
Bootstrapped Masked Autoencoders for Vision BERT Pretraining
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provid...
-
Chapter and Conference Paper
UIA-ViT: Unsupervised Inconsistency-Aware Method Based on Vision Transformer for Face Forgery Detection
Intra-frame inconsistency has been proved to be effective for the generalization of face forgery detection. However, learning to focus on these inconsistency requires extra pixel-level forged location annotati...
-
Chapter and Conference Paper
HTCN: Harmonious Text Colorization Network for Visual-Textual Presentation Design
The selection of text color is a time-consuming and important aspect in the designing of visual-textual presentation layout. In this paper, we propose a novel deep neural network architecture for predicting te...
-
Chapter and Conference Paper
Talking Face Video Generation with Editable Expression
In rencent years, the convolutional neural network have been proved to be a great success in generating talking face. Existing methods have combined a single face image with speech to generate talking face vid...
-
Chapter and Conference Paper
Towards More Powerful Multi-column Convolutional Network for Crowd Counting
Scale variation has always been one of the most challenging problems for crowd counting. By using multi-column convolutions with different receptive fields to deal with different scales in the scene, the multi...
-
Chapter and Conference Paper
Learning from Rankings with Multi-level Features for No-Reference Image Quality Assessment
Deep neural networks for image quality assessment have been suffering from a lack of training data for a long time, as it is expensive and laborious to collect sufficient subjective mean opinion scores (MOS). ...
-
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
Improving the Embedding Strategy for Batch Adaptive Steganography
Recent works have demonstrated that images with more texture regions should be selected as the sub-batch of covers to carry the total message when applying batch steganography to adaptive steganography and the...
-
Chapter and Conference Paper
Stereo Visual SLAM Using Bag of Point and Line Word Pairs
The traditional point-based SLAM algorithm performs poorly due to light changing, low-texture and highly similar scenes, while line segment features can better describe the structural information of the enviro...
-
Chapter and Conference Paper
Enhanced Video Segmentation with Object Tracking
The high efficiency and superior performance of fully convolutional network (FCN) architecture makes it a recent trend that employing FCN in video object segmentation task. While these FCN-based methods usuall...
-
Chapter and Conference Paper
Learning Cross Camera Invariant Features with CCSC Loss for Person Re-identification
Person re-identification (re-ID) is mainly deployed in the multi-camera surveillance scene, which means that learning cross camera invariant features is highly required. In this paper, we propose a novel loss ...
-
Chapter and Conference Paper
Provably Secure Generative Steganography Based on Autoregressive Model
Synthetic data and generative models have been more and more popular with the rapid development of machine learning and artificial intelligence (AI). Consequently, generative steganography, a novel steganograp...
-
Chapter and Conference Paper
Anomaly Detection with Passive Aggressive Online Gaussian Model Estimation
Anomaly detection is an important topic for surveillance video analysis and public security management. One of the major challenges comes from the fact that there is no abnormal data for training in most cases...
-
Chapter and Conference Paper
Visual Tracking by Deep Discriminative Map
Deep neural networks which widely used in image classification and speech recognition have been successfully applied to model-free object tracking. However, during tracking, it easily falls into over-fitting p...
-
Chapter and Conference Paper
Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
Recognizing visual relationships \(\langle \) subject-predicate-object