Volume 18, Issue 4November 2022Current IssueIssue-in-Progress
Improving Feature Discrimination for Object Tracking by Structural-similarity-based Metric Learning
November 2022, Article No.: 90, pp 1–23https://doi.org/10.1145/3497746

Existing approaches usually form the tracking task as an appearance matching procedure. However, the discrimination ability of appearance features is insufficient in these trackers, which is caused by their weak feature supervision constraints and ...

Decoupled Low-Light Image Enhancement
November 2022, Article No.: 92, pp 1–19https://doi.org/10.1145/3498341

The visual quality of photographs taken under imperfect lightness conditions can be degenerated by multiple factors, e.g., low lightness, imaging noise, color distortion, and so on. Current low-light image enhancement models focus on the improvement of ...

Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
November 2022, Article No.: 93, pp 1–18https://doi.org/10.1145/3498340

Visual attention in Visual Question Answering (VQA) targets at locating the right image regions regarding the answer prediction, offering a powerful technique to promote multi-modal understanding. However, recent studies have pointed out that the ...

Detection of AI-Manipulated Fake Faces via Mining Generalized Features
November 2022, Article No.: 94, pp 1–23https://doi.org/10.1145/3499026

Recently, AI-manipulated face techniques have developed rapidly and constantly, which has raised new security issues in society. Although existing detection methods consider different categories of fake faces, the performance on detecting the fake faces ...

Cross-modal Graph Matching Network for Image-text Retrieval
November 2022, Article No.: 95, pp 1–23https://doi.org/10.1145/3499027

Image-text retrieval is a fundamental cross-modal task whose main idea is to learn image-text matching. Generally, according to whether there exist interactions during the retrieval process, existing image-text retrieval methods can be classified into ...

Generation of Realistic Synthetic Financial Time-series
November 2022, Article No.: 96, pp 1–27https://doi.org/10.1145/3501305

Financial markets have always been a point of interest for automated systems. Due to their complex nature, financial algorithms and fintech frameworks require vast amounts of data to accurately respond to market fluctuations. This data availability is ...

Clustering Matters: Sphere Feature for Fully Unsupervised Person Re-identification
November 2022, Article No.: 97, pp 1–18https://doi.org/10.1145/3501404

In person re-identification (Re-ID), the data annotation cost of supervised learning, is huge and it cannot adapt well to complex situations. Therefore, compared with supervised deep learning methods, unsupervised methods are more in line with actual ...

Open Access
Harmonious Multi-branch Network for Person Re-identification with Harder Triplet Loss
November 2022, Article No.: 98, pp 1–21https://doi.org/10.1145/3501405

Recently, advances in person re-identification (Re-ID) has benefitted from use of the popular multi-branch network. However, performing feature learning in a single branch with uniform partitioning is likely to separate meaningful local regions, and ...

Towards Corruption-Agnostic Robust Domain Adaptation
November 2022, Article No.: 99, pp 1–16https://doi.org/10.1145/3501800

Great progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domains are independent and identically distributed with training target domains. However, due to unpredictable ...

Open Access
Joint Source-Channel Decoding of Polar Codes for HEVC-Based Video Streaming
November 2022, Article No.: 100, pp 1–23https://doi.org/10.1145/3502208

Ultra High-Definition (UHD) and Virtual Reality (VR) video streaming over 5G networks are emerging, in which High-Efficiency Video Coding (HEVC) is used as source coding to compress videos more efficiently and polar code is used as channel coding to ...

Densely Enhanced Semantic Network for Conversation System in Social Media
November 2022, Article No.: 101, pp 1–24https://doi.org/10.1145/3501799

The human–computer conversation system is a significant application in the field of multimedia. To select an appropriate response, retrieval-based systems model the matching between the dialogue history and response candidates. However, most of the ...

NR-CNN: Nested-Residual Guided CNN In-loop Filtering for Video Coding
November 2022, Article No.: 102, pp 1–22https://doi.org/10.1145/3502723

Recently, deep learning for video coding, such as deep predictive coding, deep transform coding, and deep in-loop filtering, has been an emerging research area. The coding gain of hybrid coding framework could be extensively promoted by the data-driven ...

FasterPose: A Faster Simple Baseline for Human Pose Estimation
November 2022, Article No.: 103, pp 1–16https://doi.org/10.1145/3503464

The performance of human pose estimation depends on the spatial accuracy of keypoint localization. Most existing methods pursue the spatial accuracy through learning the high-resolution (HR) representation from input images. By the experimental analysis, ...

Scenario-Aware Recurrent Transformer for Goal-Directed Video Captioning
November 2022, Article No.: 104, pp 1–17https://doi.org/10.1145/3503927

Fully mining visual cues to aid in content understanding is crucial for video captioning. However, most state-of-the-art video captioning methods are limited to generating captions purely based on straightforward information while ignoring the scenario ...

Online Correction of Camera Poses for the Surround-view System: A Sparse Direct Approach
November 2022, Article No.: 106, pp 1–24https://doi.org/10.1145/3505252

The surround-view module is an indispensable component of a modern advanced driving assistance system. By calibrating the intrinsics and extrinsics of the surround-view cameras accurately, a top-down surround-view can be generated from raw fisheye images. ...

Multi-granularity Brushstrokes Network for Universal Style Transfer
November 2022, Article No.: 107, pp 1–17https://doi.org/10.1145/3506710

Neural style transfer has been developed in recent years, where both performance and efficiency have been greatly improved. However, most existing methods do not transfer the brushstrokes information of style images well. In this article, we address this ...

Pansharpening Scheme Using Bi-dimensional Empirical Mode Decomposition and Neural Network
November 2022, Article No.: 108, pp 1–22https://doi.org/10.1145/3506709

The pansharpening is a combination of multispectral (MS) and panchromatic (PAN) images that produce a high-spatial-spectral-resolution MS images. In multiresolution analysis–based pansharpening schemes, some spatial and spectral distortions are found. It ...

An End-to-end Heterogeneous Restraint Network for RGB-D Cross-modal Person Re-identification
November 2022, Article No.: 109, pp 1–22https://doi.org/10.1145/3506708

The RGB-D cross-modal person re-identification (re-id) task aims to identify the person of interest across the RGB and depth image modes. The tremendous discrepancy between these two modalities makes this task difficult to tackle. Few researchers pay ...

A Spatial Relationship Preserving Adversarial Network for 3D Reconstruction from a Single Depth View
November 2022, Article No.: 110, pp 1–22https://doi.org/10.1145/3506733

Recovering the geometry of an object from a single depth image is an interesting yet challenging problem. While previous learning based approaches have demonstrated promising performance, they don’t fully explore spatial relationships of objects, which ...

ESRNet: Efficient Search and Recognition Network for Image Manipulation Detection
November 2022, Article No.: 111, pp 1–23https://doi.org/10.1145/3506853

With the widespread use of smartphones and the rise of intelligent software, we can manipulate captured photos anytime and anywhere, so the fake photos finally obtained look “Real.” If these intelligent operation methods are maliciously applied to our ...

A Novel Multi-Sample Generation Method for Adversarial Attacks
November 2022, Article No.: 112, pp 1–21https://doi.org/10.1145/3506852

Deep learning models are widely used in daily life, which bring great convenience to our lives, but they are vulnerable to attacks. How to build an attack system with strong generalization ability to test the robustness of deep learning systems is a hot ...

Accelerating Transform Algorithm Implementation for Efficient Intra Coding of 8K UHD Videos
November 2022, Article No.: 113, pp 1–20https://doi.org/10.1145/3507970

Real-time ultra-high-definition (UHD) video applications have attracted much attention, where the encoder side urgently demands the high-throughput two-dimensional (2D) transform hardware implementation for the latest video coding standards. This article ...


Currently Not Available icon

Currently Not Available


About Cookies On This Site

We use cookies to ensure that we give you the best experience on our website.

Learn more

Got it!